154 citations · 605 across the 50 of their papers we have counts for
46 papers · 1 filter
PixGR: Pixel-Space Generative Decoding for Fast Feed-Forward 3D Reconstruction
Ranran Huang, Wenjing Bian, Weixun Luo +2
We present PixGR, an efficient framework that integrates lightweight pixel-space generative modeling into feed-forward 3D Gaussian reconstruction to model scene uncertainty. Contex…
Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching
Junpeng Jing, Ronglai Zuo, Zhelun Shen +5
Recent advances in stereo matching have achieved remarkable accuracy, but often rely on large models, heavy computation, or additional foundation-model priors, making them difficul…
RGB-Pointmap Pretraining for Unified 3D Scene Understanding
Ye Mao, Weixun Luo, Ranran Huang +2
Pretraining 3D encoders through alignment with Contrastive Language-Image Pre-training (CLIP) has emerged as a promising direction for learning generalizable representations for 3D…
From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis
Ranran Huang, Weixun Luo, Ye Mao +1
In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no p…
POMA-3D: The Point Map Way to 3D Scene Understanding
Ye Mao, Weixun Luo, Ranran Huang +2
In this paper, we introduce POMA-3D, the first self-supervised 3D representation model learned from point maps. Point maps encode explicit 3D coordinates on a structured 2D grid, p…
Lite Any Stereo: Efficient Zero-Shot Stereo Matching
Junpeng Jing, Weixun Luo, Ye Mao +1
Recent advances in stereo matching have focused on accuracy, often at the cost of significantly increased model size. Traditionally, the community has regarded efficient models as…
UCorr: Wire Detection and Depth Estimation for Autonomous Drones
Benedikt Kolbeinsson, Krystian Mikolajczyk
In the realm of fully autonomous drones, the accurate detection of obstacles is paramount to ensure safe navigation and prevent collisions. Among these challenges, the detection of…
SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
Ranran Huang, Krystian Mikolajczyk
We introduce SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth poses during training or inference.…
No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views
Ranran Huang, Krystian Mikolajczyk
We introduce SPFSplat, an efficient framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth poses during training or inference. It employs a sh…
Stereo Any Video: Temporally Consistent Stereo Matching
Junpeng Jing, Weixun Luo, Ye Mao +1
This paper introduces Stereo Any Video, a powerful framework for video stereo matching. It can estimate spatially accurate and temporally consistent disparities without relying on…
Hypo3D: Exploring Hypothetical Reasoning in 3D
Ye Mao, Weixun Luo, Junpeng Jing +2
The rise of vision-language foundation models marks an advancement in bridging the gap between human and machine capabilities in 3D scene reasoning. Existing 3D reasoning benchmark…
Match Stereo Videos via Bidirectional Alignment
Junpeng Jing, Ye Mao, Anlan Qiu +1
Video stereo matching is the task of estimating consistent disparity maps from rectified stereo videos. There is considerable scope for improvement in both datasets and methods wit…
OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images
Ye Mao, Junpeng Jing, Krystian Mikolajczyk
Recent open-world 3D representation learning methods using Vision-Language Models (VLMs) to align 3D point cloud with image-text information have shown superior 3D zero-shot perfor…
Language-Based Depth Hints for Monocular Depth Estimation
Dylan Auty, Krystian Mikolajczyk
Monocular depth estimation (MDE) is inherently ambiguous, as a given image may result from many different 3D scenes and vice versa. To resolve this ambiguity, an MDE system must ma…
Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching
Junpeng Jing, Ye Mao, Krystian Mikolajczyk
Dynamic stereo matching is the task of estimating consistent disparities from stereo videos with dynamic objects. Recent learning-based methods prioritize optimal performance on a…
Learning to Project for Cross-Task Knowledge Distillation
Dylan Auty, Roy Miles, Benedikt Kolbeinsson +1
Traditional knowledge distillation (KD) relies on a proficient teacher trained on the target task, which is not always available. In this setting, cross-task distillation can be us…
DDOS: The Drone Depth and Obstacle Segmentation Dataset
Benedikt Kolbeinsson, Krystian Mikolajczyk
The advancement of autonomous drones, essential for sectors such as remote sensing and emergency services, is hindered by the absence of training datasets that fully capture the en…
Understanding the Role of the Projector in Knowledge Distillation
Roy Miles, Krystian Mikolajczyk
In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely t…
Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion
Benedikt Kolbeinsson, Krystian Mikolajczyk
Semantic segmentation from aerial views is a crucial task for autonomous drones, as they rely on precise and accurate segmentation to navigate safely and efficiently. However, aeri…
ObjCAViT: Improving Monocular Depth Estimation Using Natural Language Models And Image-Object Cross-Attention
Dylan Auty, Krystian Mikolajczyk
While monocular depth estimation (MDE) is an important problem in computer vision, it is difficult due to the ambiguity that results from the compression of a 3D scene into only 2…
Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems
Dylan Auty, Krystian Mikolajczyk
Monocular depth estimation (MDE) aims to transform an RGB image of a scene into a pixelwise depth map from the same camera view. It is fundamentally ill-posed due to missing inform…
NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning
Tony Ng, Hyo Jin Kim, Vincent Lee +7
In the light of recent analyses on privacy-concerning scene revelation from visual descriptors, we develop descriptors that conceal the input image content. In particular, we propo…
ScaleNet: A Shallow Architecture for Scale Estimation
Axel Barroso-Laguna, Yurun Tian, Krystian Mikolajczyk
In this paper, we address the problem of estimating scale factors between images. We formulate the scale estimation problem as a prediction of a probability distribution over scale…
Information Theoretic Representation Distillation
Roy Miles, Adrian Lopez Rodriguez, Krystian Mikolajczyk
Despite the empirical success of knowledge distillation, current state-of-the-art methods are computationally expensive to train, which makes them difficult to adopt in practice. T…