6 papers
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
Haonan Han, Jiancheng Huang, Xiaopeng Sun +7
Beneath the stunning visual fidelity of modern AIGC models lies a "logical desert", where systems fail tasks that require physical, causal, or complex spatial reasoning. Current ev…
Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis
Zihao Liu, Mingwen Ou, Zunnan Xu +4
Automating the synthesis of coordinated bimanual piano performances poses significant challenges, particularly in capturing the intricate choreography between the hands while prese…
REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment
Haonan Han, Rui Yang, Huan Liao +6
Traditional image-to-3D models often struggle with scenes containing multiple objects due to biases and occlusion complexities. To address this challenge, we present REPARO, a nove…
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
Zunnan Xu, Yukang Lin, Haonan Han +4
Gesture synthesis is a vital realm of human-computer interaction, with wide-ranging applications across various fields like film, robotics, and virtual reality. Recent advancements…
Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
Jiaqi Huang, Zunnan Xu, Ting Liu +4
In the domain of computer vision, Parameter-Efficient Tuning (PET) is increasingly replacing the traditional paradigm of pre-training followed by full fine-tuning. PET is particula…
AToM: Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward
Haonan Han, Xiangzuo Wu, Huan Liao +5
Recently, text-to-motion models have opened new possibilities for creating realistic human motion with greater efficiency and flexibility. However, aligning motion generation with…