6 papers
Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li +2
Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode…
Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers
Shuhong Zheng, Michael Oechsle, Erik Sandström +3
Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. Howe…
Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling
Shuhong Zheng, Ashkan Mirzaei, Igor Gilitschenski
Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject acros…
Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models
Shuhong Zheng, Zhipeng Bao, Ruoyu Zhao +2
Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion mode…
Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding
Yunze Man, Shuhong Zheng, Zhipeng Bao +3
Complex 3D scene understanding has gained increasing attention, with scene encoding strategies playing a crucial role in this success. However, the optimal scene encoding strategie…
Multi-task View Synthesis with Neural Radiance Fields
Shuhong Zheng, Zhipeng Bao, Martial Hebert +1
Multi-task visual learning is a critical aspect of computer vision. Current research, however, predominantly concentrates on the multi-task dense prediction setting, which overlook…