New Era Artificial Intelligence

community

AI & ML interests

None defined yet.

Recent Activity

NewEraAI's activity

DmitryRyuminĀ 
posted an update 3 months ago
view post
Post
2602
šŸ”„šŸŽ­šŸŒŸ New Research Alert - HeadGAP (Avatars Collection)! šŸŒŸšŸŽ­šŸ”„
šŸ“„ Title: HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors šŸ”

šŸ“ Description: HeadGAP introduces a novel method for generating high-fidelity, animatable 3D head avatars from few-shot data, using Gaussian priors and dynamic part-based modelling for personalized and generalizable results.

šŸ‘„ Authors: @zxz267 , @walsvid , @zhaohu2 , Weiyi Zhang, @hellozhuo , Xu Chang, Yang Zhao, Zheng Lv, Xiaoyuan Zhang, @yongjie-zhang-mail , Guidong Wang, and Lan Xu

šŸ“„ Paper: HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors (2408.06019)

šŸŒ Github Page: https://headgap.github.io

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #HeadGAP #3DAvatar #FewShotLearning #GaussianPriors #AvatarCreation #3DModeling #MachineLearning #ComputerVision #ComputerGraphics #GenerativeAI #DeepLearning #AI
DmitryRyuminĀ 
posted an update 3 months ago
view post
Post
2043
šŸš€šŸ•ŗšŸŒŸ New Research Alert - ECCV 2024 (Avatars Collection)! šŸŒŸšŸ’ƒšŸš€
šŸ“„ Title: Expressive Whole-Body 3D Gaussian Avatar šŸ”

šŸ“ Description: ExAvatar is a model that generates animatable 3D human avatars with facial expressions and hand movements from short monocular videos using a hybrid mesh and 3D Gaussian representation.

šŸ‘„ Authors: Gyeongsik Moon, Takaaki Shiratori, and @psyth

šŸ“… Conference: ECCV, 29 Sep ā€“ 4 Oct, 2024 | Milano, Italy šŸ‡®šŸ‡¹

šŸ“„ Paper: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (2407.08414)

šŸ“„ Paper: Expressive Whole-Body 3D Gaussian Avatar (2407.21686)

šŸŒ Github Page: https://mks0601.github.io/ExAvatar
šŸ“ Repository: https://github.com/mks0601/ExAvatar_RELEASE

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #ExAvatar #3DAvatar #FacialExpressions #HandMotions #MonocularVideo #3DModeling #GaussianSplatting #MachineLearning #ComputerVision #ComputerGraphics #DeepLearning #AI #ECCV2024
DmitryRyuminĀ 
posted an update 3 months ago
view post
Post
1854
šŸ”„šŸŽ­šŸŒŸ New Research Alert - ECCV 2024 (Avatars Collection)! šŸŒŸšŸŽ­šŸ”„
šŸ“„ Title: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos šŸ”

šŸ“ Description: MeshAvatar is a novel pipeline that generates high-quality triangular human avatars from multi-view videos, enabling realistic editing and rendering through a mesh-based approach with physics-based decomposition.

šŸ‘„ Authors: Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, and Yebin Liu

šŸ“… Conference: ECCV, 29 Sep ā€“ 4 Oct, 2024 | Milano, Italy šŸ‡®šŸ‡¹

šŸ“„ Paper: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (2407.08414)

šŸŒ Github Page: https://shad0wta9.github.io/meshavatar-page
šŸ“ Repository: https://github.com/shad0wta9/meshavatar

šŸ“ŗ Video: https://www.youtube.com/watch?v=Kpbpujkh2iI

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #MeshAvatar #3DAvatars #MultiViewVideo #PhysicsBasedRendering #TriangularMesh #AvatarCreation #3DModeling #NeuralRendering #Relighting #AvatarEditing #MachineLearning #ComputerVision #ComputerGraphics #DeepLearning #AI #ECCV2024
NiansuhĀ 
posted an update 4 months ago
view post
Post
2539
Plugins in NiansuhAI

Plugin Names:
1. WebSearch: Searches the web using search engines.
2. Calculator: Evaluates mathematical expressions, extending the base Tool class.
3. WebBrowser: Extracts and summarizes information from web pages.
4. Wikipedia: Retrieves information from Wikipedia using its API.
5. Arxiv: Searches and fetches article information from Arxiv.
6. WolframAlphaTool: Provides answers on math, science, technology, culture, society, and everyday life.

These plugins currently support the GPT-4O-2024-08-06 model, which also supports image analysis.

Try it now: https://huggingface.co/spaces/NiansuhAI/chat

Similar to: https://hf.co/chat
NiansuhĀ 
posted an update 5 months ago
view post
Post
2757
Introducing Plugins in NiansuhAI (on July 20, 2024)

Plugin Names:
1. WebSearch: Tool for searching the web using search engines.
2. Calculator: Helps evaluate mathematical expressions; extends the base Tool class.
3. WebBrowser: Interacts with web pages to extract information or summarize content.
4. Wikipedia: Retrieves data from Wikipedia using its API.
5. Arxiv: Searches and fetches article information from Arxiv.
6. WolframAlphaTool: Answers questions on Math, Science, Technology, Culture, Society, and Everyday Life.

Similar to https://hf.co/chat
DmitryRyuminĀ 
posted an update 5 months ago
view post
Post
2300
šŸš€šŸ•ŗšŸŒŸ New Research Alert - CVPR 2024 (Avatars Collection)! šŸŒŸšŸ’ƒšŸš€
šŸ“„ Title: IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing šŸ”

šŸ“ Description: IntrinsicAvatar is a method for extracting high-quality geometry, albedo, material, and lighting properties of clothed human avatars from monocular videos using explicit ray tracing and volumetric scattering, enabling realistic animations under varying lighting conditions.

šŸ‘„ Authors: Shaofei Wang, Božidar Antić, Andreas Geiger, and Siyu Tang

šŸ“… Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŸ‡ŗšŸ‡ø

šŸ”— Paper: IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing (2312.05210)

šŸŒ Github Page: https://neuralbodies.github.io/IntrinsicAvatar/
šŸ“ Repository: https://github.com/taconite/IntrinsicAvatar

šŸ“ŗ Video: https://www.youtube.com/watch?v=aS8AIxgVXzI

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #IntrinsicAvatar #InverseRendering #MonocularVideos #RayTracing #VolumetricScattering #3DReconstruction #MachineLearning #ComputerVision #DeepLearning #AI #CVPR2024
DmitryRyuminĀ 
posted an update 5 months ago
view post
Post
3139
šŸ”„šŸŽ­šŸŒŸ New Research Alert - ECCV 2024 (Avatars Collection)! šŸŒŸšŸŽ­šŸ”„
šŸ“„ Title: RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models šŸ”

šŸ“ Description: RodinHD generates high-fidelity 3D avatars from portrait images using a novel data scheduling strategy and weight consolidation regularization to capture intricate details such as hairstyles.

šŸ‘„ Authors: Bowen Zhang, @yiji , @chunyuwang , Ting Zhang, @jiaolong , Yansong Tang, Feng Zhao, Dong Chen, and Baining Guo

šŸ“… Conference: ECCV, 29 Sep ā€“ 4 Oct, 2024 | Milano, Italy šŸ‡®šŸ‡¹

šŸ“„ Paper: RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models (2407.06938)

šŸŒ Github Page: https://rodinhd.github.io/
šŸ“ Repository: https://github.com/RodinHD/RodinHD

šŸ“ŗ Video: https://www.youtube.com/watch?v=ULvHt7dZx-Q

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #RodinHD #3DAvatars #DiffusionModels #HighFidelity #PortraitTo3D #MachineLearning #ComputerVision #DeepLearning #AI #ECCV2024
NiansuhĀ 
posted an update 5 months ago
DmitryRyuminĀ 
posted an update 6 months ago
view post
Post
2424
šŸ”„šŸŽ­šŸŒŸ New Research Alert - LivePortrait (Avatars Collection)! šŸŒŸšŸŽ­šŸ”„
šŸ“„ Title: LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control šŸ”

šŸ“ Description: LivePortrait is an efficient video-driven portrait animation framework that uses implicit keypoints and stitching/retargeting modules to generate high-quality, controllable animations from a single source image.

šŸ‘„ Authors: @cleardusk , Dingyun Zhang, Xiaoqiang Liu, Zhizhou Zhong, Yuan Zhang, Pengfei Wan, and Di Zhang

šŸ¤— Demo: KwaiVGI/LivePortrait

šŸ“„ Paper: LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control (2407.03168)

šŸŒ Github Page: https://liveportrait.github.io/
šŸ“ Repository: https://github.com/KwaiVGI/LivePortrait

šŸ”„ Model šŸ¤–: KwaiVGI/LivePortrait

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #LivePortrait #PortraitAnimation #ComputerVision #MachineLearning #DeepLearning #ComputerGraphics #FacialAnimation #GenerativeAI #RealTimeRendering #AI
DmitryRyuminĀ 
posted an update 6 months ago
view post
Post
2728
šŸš€šŸ•ŗšŸŒŸ New Research Alert (Avatars Collection)! šŸŒŸšŸ’ƒšŸš€
šŸ“„ Title: Expressive Gaussian Human Avatars from Monocular RGB Video šŸ”

šŸ“ Description: The new EVA model enhances the expressiveness of digital avatars by using 3D Gaussians and SMPL-X to capture fine-grained hand and face details from monocular RGB video.

šŸ‘„ Authors: Hezhen Hu, Zhiwen Fan, Tianhao Wu, Yihan Xi, Seoyoung Lee, Georgios Pavlakos, and Zhangyang Wang

šŸ“„ Paper: Expressive Gaussian Human Avatars from Monocular RGB Video (2407.03204)

šŸŒ Github Page: https://evahuman.github.io/
šŸ“ Repository: https://github.com/evahuman/EVA

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #DigitalAvatars #3DModeling #ComputerVision #MonocularVideo #SMPLX #3DGaussians #AvatarExpressiveness #HandTracking #FacialExpressions #AI #MachineLearning
DmitryRyuminĀ 
posted an update 6 months ago
view post
Post
2053
šŸ”„šŸŽ­šŸŒŸ New Research Alert - ECCV 2024 (Avatars Collection)! šŸŒŸšŸŽ­šŸ”„
šŸ“„ Title: Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture šŸ”

šŸ“ Description: Topo4D is a novel method for automated, high-fidelity 4D head tracking that optimizes dynamic topological meshes and 8K texture maps from multi-view time-series images.

šŸ‘„ Authors: @Dazz1e , Y. Cheng, @Ryan-sjtu , H. Jia, D. Xu, W. Zhu, Y. Yan

šŸ“… Conference: ECCV, 29 Sep ā€“ 4 Oct, 2024 | Milano, Italy šŸ‡®šŸ‡¹

šŸ“„ Paper: Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture (2406.00440)

šŸŒ Github Page: https://xuanchenli.github.io/Topo4D/
šŸ“ Repository: https://github.com/XuanchenLi/Topo4D

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸš€ WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers

šŸš€ ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #Topo4D #4DHead #3DModeling #4DCapture #FacialAnimation #ComputerGraphics #MachineLearning #HighFidelity #TextureMapping #DynamicMeshes #GaussianSplatting #VisualEffects #ECCV2024
  • 1 reply
Ā·
DmitryRyuminĀ 
posted an update 6 months ago
view post
Post
3639
šŸš€šŸŽ­šŸŒŸ New Research Alert - Portrait4D-v2 (Avatars Collection)! šŸŒŸšŸŽ­šŸš€
šŸ“„ Title: Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer šŸ”

šŸ“ Description: Portrait4D-v2 is a novel method for one-shot 4D head avatar synthesis using pseudo multi-view videos and a vision transformer backbone, achieving superior performance without relying on 3DMM reconstruction.

šŸ‘„ Authors: Yu Deng, Duomin Wang, and Baoyuan Wang

šŸ“„ Paper: Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer (2403.13570)

šŸŒ GitHub Page: https://yudeng.github.io/Portrait4D-v2/
šŸ“ Repository: https://github.com/YuDeng/Portrait-4D

šŸ“ŗ Video: https://www.youtube.com/watch?v=5YJY6-wcOJo

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: Portrait4D #4DAvatar #HeadSynthesis #3DModeling #TechInnovation #DeepLearning #ComputerGraphics #ComputerVision #Innovation
  • 1 reply
Ā·
NiansuhĀ 
posted an update 6 months ago
DmitryRyuminĀ 
posted an update 6 months ago
view post
Post
2364
šŸ˜€šŸ˜²šŸ˜šŸ˜” New Research Alert - CVPRW 2024 (Facial Expressions Recognition Collection)! šŸ˜”šŸ˜„šŸ„“šŸ˜±
šŸ“„ Title: Zero-Shot Audio-Visual Compound Expression Recognition Method based on Emotion Probability Fusion šŸ”

šŸ“ Description: AVCER is a novel audio-visual method for compound expression recognition based on pair-wise sum of emotion probability, evaluated in multi- and cross-corpus setups without task-specific training data, demonstrating its potential for intelligent emotion annotation tools.

šŸ‘„ Authors: @ElenaRyumina , Maxim Markitantov, @DmitryRyumin , Heysem Kaya, and Alexey Karpov

šŸ“… Conference: CVPRW, Jun 17-21, 2024 | Seattle WA, USA šŸ‡ŗšŸ‡ø

šŸ¤— Demo: ElenaRyumina/AVCER

šŸ“„ Paper: Audio-Visual Compound Expression Recognition Method based on Late Modality Fusion and Rule-based Decision (2403.12687)

šŸŒ Github Page: https://elenaryumina.github.io/AVCER
šŸ“ Repository: https://github.com/ElenaRyumina/AVCER/tree/main/src

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Facial Expressions Recognition Collection: DmitryRyumin/facial-expressions-recognition-65f22574e0724601636ddaf7

šŸ” Keywords: #AVCER #AudioVisual #CompoundExpressions #EmotionRecognition #ModalityFusion #RuleBasedAI #ABAWCompetition #AIResearch #HumanEmotion #IntelligentTools #MachineLearning #DeepLearning #MultiCorpus #CrossCorpus #CVPR2024
DmitryRyuminĀ 
posted an update 7 months ago
view post
Post
1869
šŸš€šŸŽ­šŸŒŸ New Research Alert - CVPR 2024 (Avatars Collection)! šŸŒŸšŸŽ­šŸš€
šŸ“„ Title: Relightable Gaussian Codec Avatars šŸ”

šŸ“ Description: Relightable Gaussian Codec Avatars is a method for creating highly detailed and relightable 3D head avatars that can animate expressions in real time and support complex features such as hair and skin with efficient rendering suitable for VR.

šŸ‘„ Authors: @psyth , @GBielXONE02 , Tomas Simon, Junxuan Li, and @giljoonam

šŸ“… Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŸ‡ŗšŸ‡ø

šŸ“„ Paper: Relightable Gaussian Codec Avatars (2312.03704)

šŸŒ GitHub Page: https://shunsukesaito.github.io/rgca/

šŸš€ CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #3DAvatars #RealTimeRendering #RelightableAvatars #3DModeling #VirtualReality #CVPR2024 #DeepLearning #ComputerGraphics #ComputerVision #Innovation #VR
DmitryRyuminĀ 
posted an update 7 months ago
view post
Post
830
šŸš€šŸŽ­šŸŒŸ New Research Alert - InstructAvatar (Avatars Collection)! šŸŒŸšŸŽ­šŸš€
šŸ“„ Title: InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation šŸ”

šŸ“ Description: InstructAvatar is a novel method for generating emotionally expressive 2D avatars using text-guided instructions, offering improved emotion control, lip-sync quality, and naturalness. It uses a two-branch diffusion-based generator to predict avatars based on both audio and text input.

šŸ‘„ Authors: Yuchi Wang et al.

šŸ“„ Paper: InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation (2405.15758)

šŸŒ Github Page: https://wangyuchi369.github.io/InstructAvatar/
šŸ“ Repository: https://github.com/wangyuchi369/InstructAvatar

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #InstructAvatar #AvatarGeneration #EmotionControl #FacialMotion #LipSynchronization #NaturalLanguageInterface #DiffusionBasedGenerator #TextGuidedInstructions #2DAvatars #VideoSynthesis #Interactivity #ComputerGraphics #DeepLearning #ComputerVision #Innovation
NiansuhĀ 
posted an update 7 months ago
view post
Post
1117
**Model Names:** gpt-4-turbo-preview, gpt-4-vision-preview, gpt-3.5-turbo-16k
**Searchable Models:** Creative, Balanced, Precise

Image creation will be available soon in NiansuhAI.
**Model Name:** DALL-E 3

https://huggingface.co/spaces/NiansuhAI/LLMs1
---
  • 2 replies
Ā·
DmitryRyuminĀ 
posted an update 7 months ago
view post
Post
1492
šŸ”„šŸš€šŸŒŸ New Research Alert - YOLOv10! šŸŒŸšŸš€šŸ”„
šŸ“„ Title: YOLOv10: Real-Time End-to-End Object Detection šŸ”

šŸ“ Description: YOLOv10 improves real-time object recognition by eliminating non-maximum suppression and optimizing the model architecture to achieve state-of-the-art performance with lower latency and computational overhead.

šŸ‘„ Authors: Ao Wang et al.

šŸ“„ Paper: YOLOv10: Real-Time End-to-End Object Detection (2405.14458)

šŸ¤— Demo: kadirnar/Yolov10 curated by @kadirnar
šŸ”„ Model šŸ¤–: kadirnar/Yolov10

šŸ“ Repository: https://github.com/THU-MIG/yolov10

šŸ“® Post about YOLOv9 - https://huggingface.co/posts/DmitryRyumin/519784698531054

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸ” Keywords: #YOLOv10 #ObjectDetection #RealTimeAI #ModelOptimization #MachineLearning #DeepLearning #ComputerVision #Innovation
  • 1 reply
Ā·
DmitryRyuminĀ 
posted an update 7 months ago
view post
Post
1565
šŸš€šŸŽ­šŸŒŸ New Research Alert - Gaussian Head & Shoulders (Avatars Collection)! šŸŒŸšŸŽ­šŸš€
šŸ“„ Title: Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping šŸ”

šŸ“ Description: Gaussian Head & Shoulders is a method for creating high-fidelity upper body avatars by integrating 3D morphable head models with a neural texture warping approach to overcome the limitations of Gaussian splatting.

šŸ‘„ Authors: Tianhao Wu et al.

šŸ“„ Paper: Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping (2405.12069)

šŸŒ Github Page: https://gaussian-head-shoulders.netlify.app

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸš€ Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36

šŸ” Keywords: #3DModeling #NeuralAvatars #GaussianSplatting #HighFidelityAvatars #3DReconstruction #AvatarRendering #TextureWarping #ComputerGraphics #DeepLearning #ComputerVision #Innovation
DmitryRyuminĀ 
posted an update 7 months ago
view post
Post
1762
šŸš€šŸ¤–šŸŒŸ New Research Alert - CVPR 2024! šŸŒŸšŸ¤–šŸš€
šŸ“„ Title: RoHM: Robust Human Motion Reconstruction via Diffusion šŸ”

šŸ“ Description: RoHM is a diffusion-based approach for robust 3D human motion reconstruction from monocular RGB(-D) videos, effectively handling noise and occlusions to produce complete and coherent motions. This method outperforms current techniques in various tasks and is faster at test time.

šŸ‘„ Authors: Siwei Zhang et al.

šŸ“… Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŸ‡ŗšŸ‡ø

šŸ“„ Paper: RoHM: Robust Human Motion Reconstruction via Diffusion (2401.08570)

šŸŒ GitHub Page: https://sanweiliti.github.io/ROHM/ROHM.html
šŸ“ Repository: https://github.com/sanweiliti/RoHM

šŸš€ Added to the CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers

šŸ“š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin

šŸ” Keywords: #RoHM #HumanMotionReconstruction #DiffusionModels #3DAnimation #CVPR2024 #DeepLearning #ComputerVision #Innovation