paper-with-me

홈 › Papers

Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video

2020-11-17 · CVPR 2021 1 · Hongsuk Choi, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

Despite the recent success of single image-based 3D human pose and shape estimation methods, recovering temporally consistent and smooth 3D human motion from a video is still challenging. Several video-based methods have been proposed; however, they fail to resolve the single image-based methods' temporal inconsistency issue due to a strong dependency on a static feature of the current frame. In this regard, we present a temporally consistent mesh recovery system (TCMR). It effectively focuses on the past and future frames' temporal information without being dominated by the current static feature. Our TCMR significantly outperforms previous video-based methods in temporal consistency with better per-frame 3D pose and shape accuracy. We also release the codes. For the demo video, see https://youtu.be/WB3nTnSQDII. For the codes, see https://github.com/hongsukchoi/TCMR_RELEASE.

📄 PDF Abstract BibTeX arXiv:2011.08627

Code (1)

hongsukchoi/TCMR_RELEASE 공식 구현 pytorch

Tasks

3D human pose and shape estimation3D Human Pose Estimation

Similar Papers 제목 키워드 기반

Mamba-Enhanced Implicit Motion Learning for Audio-Driven Portrait Animation

2026-06-02 · Xuan Wei, Jiahui Chen, Kaiheng Li, Mingyu Shao 외 arxiv

Audio-driven human motion video generation aims to synthesize realistic and temporally coherent human animations from a single static image, with applications in talking-head synthesis, co-speech gesture generation, and …

Gesture GenerationVideo Generation

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models

2024-07-12 · Jeongho Kim, Min-Jung Kim, Junsoo Lee, Jaegul Choo

Pose-driven human-image animation diffusion models have shown remarkable capabilities in realistic human video synthesis. Despite the promising results achieved by previous approaches, challenges persist in achieving tem…

Image Animation

From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction

2026-02-02 · Xingyu Miao, Junting Dong, Qin Zhao, Yuhang Yang 외 arxiv

In this work, we focus on the challenge of temporally consistent human-centric dense prediction across video sequences. Existing models achieve strong per-frame accuracy but often flicker under motion, occlusion, and lig…

BodyReLux: Temporally Consistent Full-Body Video Relighting

2026-05-20 · Li Ma, Mingming He, Xueming Yu, David M. George 외 arxiv

Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video diffusion-based framework for relighting full-body human performances…

Data Augmentation

Unboxed: Geometrically and Temporally Consistent Video Outpainting

2025-01-01 · CVPR 2025 1 · Zhongrui Yu, Martina Megaro-Boldini, Robert W. Sumner, Abdelaziz Djelouah

Extending the field of view of video content beyond its original version has many applications: immersive viewing experience with VR devices, reformatting 4:3 legacy content to today's viewing conditions with wide sc…

DenoisingImage Outpainting