paper-with-me

Papers

WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion

2024-03-27 · CVPR 2024 1 · Khiem Vuong, N. Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan

Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion. In this work, we introduce a novel framework for automatically generating a large, realistic dataset of dynamic objects under occlusions using freely available time-lapse imagery. By leveraging off-the-shelf 2D (bounding box, segmentation, keypoint) and 3D (pose, shape) predictions as pseudo-groundtruth, unoccluded 3D objects are identified automatically and composited into the background in a clip-art style, ensuring realistic appearances and physically accurate occlusion configurations. The resulting clip-art image with pseudo-groundtruth enables efficient training of object reconstruction methods that are robust to occlusions. Our method demonstrates significant improvements in both 2D and 3D reconstruction, particularly in scenarios with heavily occluded objects like vehicles and people in urban scenes.

📄 PDF Abstract BibTeX arXiv:2403.19022

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionObject Reconstruction

Similar Papers 제목 키워드 기반

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

2023-05-21 · NeurIPS 2023 11

We present DreamWaltz, a novel framework for generating and animating complex 3D avatars given text guidance and parametric human body prior. While recent methods have shown encouraging results for text-to-3D generation …

3D GenerationText to 3D

DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion

2024-09-25 · Yukun Huang, Jianan Wang, Ailing Zeng, Zheng-Jun Zha 외

Leveraging pretrained 2D diffusion models and score distillation sampling (SDS), recent methods have shown promising results for text-to-3D avatar generation. However, generating high-quality 3D avatars capable of expres…

Text to 3D

The Alignment Waltz: Jointly Training Agents to Collaborate for Safety

2025-10-09 · Jingyu Zhang, Haozhu Wang, Eric Michael Smith, Sid Wang 외 arxiv

Harnessing the power of LLMs requires a delicate dance between being helpful and harmless. This creates a fundamental tension between two competing challenges: vulnerability to adversarial attacks that elicit unsafe cont…

Multi-agent Reinforcement Learning

WALT: Web Agents that Learn Tools

2025-10-01 · Viraj Prabhu, Yutong Dai, Matthew Fernandez, Jing Gu 외 arxiv

Web agents promise to automate complex browser tasks, but current methods remain brittle -- relying on step-by-step UI interactions and heavy LLM reasoning that break under dynamic layouts and long horizons. Humans, by c…

Argumentation in Waltz's "Emerging Structure of International Politics''

2023-12-31 · Magdalena Wolska, Bernd Fröhlich, Katrin Girgensohn, Sassan Gholiagha 외

We present an annotation scheme for argumentative and domain-specific aspects of scholarly articles on the theory of International Relations. At argumentation level we identify Claims and Support/Attack relations. At dom…

Articles