2 citations · 5 across the 23 of their papers we have counts for
12 papers · 1 filter
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
Zeqi Xiao, Yiwei Zhao, Lingxiao Li +6
We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video…
Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
Yifan Zhou, Zeqi Xiao, Tianyi Wei +2
Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent To…
Boosting Monocular Metric Depth Estimation via Bokeh Rendering
Hangwei Zhang, Armando Fortes, Tianyi Wei +1
Bokeh rendering and depth estimation share a fundamental optical connection, yet existing methods fail to fully exploit this reciprocity. Conventional bokeh pipelines rely heavily…
ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
Honghua Chen, Yushi Lan, Yongwei Chen +1
We propose ArtiLatent, a generative framework that synthesizes human-made 3D objects with fine-grained geometry, accurate articulation, and realistic appearance. Our approach joint…
Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors
Songlin Yang, Tianyi Wei, Yushi Lan +3
Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer vision. Existing approaches suf…
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
Yushi Lan, Yihang Luo, Fangzhou Hong +7
We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-…
FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
Jeonghwan Kim, Yushi Lan, Armando Fortes +2
Recent mesh generation approaches typically tokenize triangle meshes into sequences of tokens and train autoregressive models to generate these tokens sequentially. Despite substan…
WorldMem: Long-term Consistent World Simulation with Memory
Zeqi Xiao, Yushi Lan, Yifan Zhou +4
World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context wi…
FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
Tianyi Wei, Yifan Zhou, Dongdong Chen +1
The integration of Rotary Position Embedding (RoPE) in Multimodal Diffusion Transformer (MMDiT) has significantly enhanced text-to-image generation quality. However, the fundamenta…
Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
Yifan Zhou, Zeqi Xiao, Shuai Yang +1
Latent Diffusion Models (LDMs) are known to have an unstable generation process, where even small perturbations or shifts in the input noise can lead to significantly different out…
Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models
Armando Fortes, Tianyi Wei, Shangchen Zhou +1
Recent advances in large-scale text-to-image models have revolutionized creative fields by generating visually captivating outputs from textual prompts; however, while traditional…
Textured 3D Regenerative Morphing with 3D Diffusion Prior
Songlin Yang, Yushi Lan, Honghua Chen +1
Textured 3D morphing creates smooth and plausible interpolation sequences between two 3D objects, focusing on transitions in both shape and texture. This is important for creative…