8 papers
LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
Zhijian Shu, Cheng Lin, Tao Xie +8
3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for l…
SynthDrive: Scalable Real2Sim2Real Sensor Simulation Pipeline for High-Fidelity Asset Generation and Driving Data Synthesis
Zhengqing Chen, Ruohong Mei, Xiaoyang Guo +5
In the field of autonomous driving, sensor simulation is essential for generating rare and diverse scenarios that are difficult to capture in real-world environments. Current solut…
SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization
Junyuan Deng, Heng Li, Tao Xie +4
Scene regression methods, such as VGGT, solve the Structure-from-Motion (SfM) problem by directly regressing camera poses and 3D scene structures from input images. They demonstrat…
2D Gaussians Meet Visual Tokenizer
Yiang Shi, Xiaoyang Guo, Wei Yin +5
The image tokenizer is a critical component in AR image generation, as it determines how rich and structured visual content is encoded into compact representations. Existing quanti…
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
Mingkai Jia, Wei Yin, Xiaotao Hu +5
Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the qua…
Epona: Autoregressive Diffusion World Model for Autonomous Driving
Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu +9
Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-ba…