Pixel-Perfect Visual Geometry Estimation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Gangwei, Lin, Haotong, Luo, Hongcheng, Sun, Haiyang, Wang, Bing, Chen, Guang, Peng, Sida, Ye, Hangjun, Yang, Xin
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
by: Xu, Gangwei, et al.
Published: (2025)

BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation
by: Xu, Gangwei, et al.
Published: (2025)

PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
by: Chi, Cheng, et al.
Published: (2026)

ViSE: A Systematic Approach to Vision-Only Street-View Extrapolation
by: Tan, Kaiyuan, et al.
Published: (2025)

Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes
by: Wang, Shuyun, et al.
Published: (2025)

ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
by: Tan, Kaiyuan, et al.
Published: (2025)

Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
by: Guo, Xiangyu, et al.
Published: (2025)

PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequences
by: Lin, Min, et al.
Published: (2026)

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
by: Tan, Kaiyuan, et al.
Published: (2026)

Toward Physically Consistent Driving Video World Models under Challenging Trajectories
by: Zhou, Jiawei, et al.
Published: (2026)

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
by: Chen, Xiaoxue, et al.
Published: (2025)

Generalized Geometry Encoding Volume for Real-time Stereo Matching
by: Liu, Jiaxin, et al.
Published: (2025)

ADGaussian: Generalizable Gaussian Splatting for Autonomous Driving via Multi-modal Joint Learning
by: Song, Qi, et al.
Published: (2025)

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
by: Li, Yongkang, et al.
Published: (2025)

Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation
by: Lin, Haotong, et al.
Published: (2024)

IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
by: Xu, Gangwei, et al.
Published: (2024)

Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
by: Yan, Yunzhi, et al.
Published: (2024)

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving
by: Zhu, Ziyue, et al.
Published: (2025)

LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
by: Mei, Xiaodong, et al.
Published: (2026)

Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry
by: Zhang, Zhaoxing, et al.
Published: (2024)

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation
by: Guo, Haoyu, et al.
Published: (2025)

FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagation
by: Lin, Min, et al.
Published: (2024)

PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement
by: Zheng, Haitian, et al.
Published: (2025)

Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
by: Wang, Xianqi, et al.
Published: (2024)

Quantized Visual Geometry Grounded Transformer
by: Feng, Weilun, et al.
Published: (2025)

DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
by: Xia, Tianze, et al.
Published: (2025)

Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume
by: Xu, Gangwei, et al.
Published: (2023)

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields
by: Yu, Hao, et al.
Published: (2026)

Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic Mask
by: Zhang, Shangzan, et al.
Published: (2023)

LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
by: Luo, Yuechen, et al.
Published: (2026)

Hybrid Cost Volume for Memory-Efficient Optical Flow
by: Zhao, Yang, et al.
Published: (2024)

Unlocking the Power of Critical Factors for 3D Visual Geometry Estimation
by: Xu, Guangkai, et al.
Published: (2026)

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions
by: Xu, Gangwei, et al.
Published: (2024)

Depth Anything 3: Recovering the Visual Space from Any Views
by: Lin, Haotong, et al.
Published: (2025)

PixelFlow: Pixel-Space Generative Models with Flow
by: Chen, Shoufa, et al.
Published: (2025)

PromptStereo: Zero-Shot Stereo Matching via Structure and Motion Prompts
by: Wang, Xianqi, et al.
Published: (2026)

SpatialTracker: Tracking Any 2D Pixels in 3D Space
by: Xiao, Yuxi, et al.
Published: (2024)

ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking
by: Wei, Xiaobao, et al.
Published: (2026)

From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection
by: Liu, Yepeng, et al.
Published: (2026)

Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation
by: Xu, Zhen, et al.
Published: (2025)