Ruoshi Liu

14 papers · 2021–2024 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🗺️ Taxonomy Completionist (20) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🤝 Dynamic Duo (14) ⚡ Prolific Year (8) 💎 Century Club (14)

Conferences

CVPR (5) ECCV (3) CORL (2) ICCV (2) ICLR (1) NIPS (1)

Top co-authors

Carl Vondrick (14) Pavel Tokmakov (4) Ege Ozguroglu (4) Basile Van Hoorick (3) Achal Dave (3) Rundi Wu (3) Changxi Zheng (2) Chengzhi Mao (2) Sruthi Sudhakar (2) Alper Canberk (2)

Keywords

3d reconstruction (5) diffusion model (2) occlusion reasoning (2) pose estimation (2) differentiable rendering (2) zero-shot learning (2) novel view synthesis (2) self-supervised learning (1) neural rendering (1) video prediction (1) gaussian splatting (1) loss landscape (1) hierarchical representation (1) gradient descent (1) video understanding (1) shape estimation (1) action prediction (1) image reconstruction (1) occlusion handling (1) object segmentation (1)

Papers

Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape ICLR 2024

Differentiable Robot Rendering CORL 2024

Dreamitate: Real-World Visuomotor Policy Learning via Video Generation CORL 2024

pix2gestalt: Amodal Segmentation by Synthesizing Wholes CVPR 2024

GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering CVPR 2024

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis ECCV 2024

Controlling the World by Sleight of Hand ECCV 2024

EraseDraw : Learning to Insert Objects by Erasing Them from Images ECCV 2024

Zero-1-to-3: Zero-shot One Image to 3D Object ICCV 2023

Humans As Light Bulbs: 3D Human Reconstruction From Thermal Reflection CVPR 2023

What You Can Reconstruct From a Shadow CVPR 2023

Landscape Learning for Neural Network Inversion ICCV 2023

Objaverse-XL: A Universe of 10M+ 3D Objects NIPS 2023

Learning the Predictability of the Future CVPR 2021