Search Results for author:
Found 19 papers, 16 papers with code
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models.
Optimizing LiDAR Placements for Robust Driving Perception in Adverse Conditions
The robustness of driving perception systems under unprecedented conditions is crucial for safety-critical usages.
Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Then, another VFM trained on fine-grained 2D masks is adopted to guide the generation of semantically augmented images and point clouds to enhance the performance of neural networks, which mix the data from source and target domains like view frustums (FrustumMixing).
FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation
Firstly, a frustum feature encoder module is used to extract per-point features within the frustum region, which preserves scene consistency and is crucial for point-level predictions.
Ranked #2 on
3D Semantic Segmentation
on nuScenes
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
Depth estimation from monocular images is pivotal for real-world visual perception systems.
Learning to Adapt SAM for Segmenting Cross-domain Point Clouds
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data.
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase.
Ranked #2 on
3D Semantic Segmentation
on SemanticKITTI
(using extra training data)
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception.
Towards Label-free Scene Understanding by Vision Foundation Models
For nuImages and nuScenes datasets, the performance is 22. 1\% and 26. 8\% with improvements of 3. 5\% and 6. 0\%, respectively.
SAD: Segment Any RGBD
The Segment Anything Model (SAM) has demonstrated its effectiveness in segmenting any part of 2D RGB images.
Open Vocabulary Semantic Segmentation
Panoptic Segmentation
+1
RoboBEV: Towards Robust Bird's Eye View Perception under Corruptions
Our experiments further demonstrate that pre-training and depth-free BEV transformation has the potential to enhance out-of-distribution robustness.
Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications.
Rethinking Range View Representation for LiDAR Segmentation
We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i. e., SemanticKITTI, nuScenes, and ScribbleKITTI.
Ranked #4 on
3D Semantic Segmentation
on SemanticKITTI
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
For the first time, our pre-trained network achieves annotation-free 3D semantic segmentation with 20. 8% and 25. 08% mIoU on nuScenes and ScanNet, respectively.
Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information.
LaserMix for Semi-Supervised LiDAR Semantic Segmentation
Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods.
ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation
We present ConDA, a concatenation-based domain adaptation framework for LiDAR segmentation that: 1) constructs an intermediate domain consisting of fine-grained interchange signals from both source and target domains without destabilizing the semantic coherency of objects and background around the ego-vehicle; and 2) utilizes the intermediate domain for self-training.
Free Lunch for Co-Saliency Detection: Context Adjustment
We hope that the scale, diversity, and quality of our dataset can benefit researchers in this area and beyond.
