Papers 2D Semantic Segmentation
“2D Semantic Segmentation” 태그가 달린 논문 88편 · 필터 해제
SAM3 Self-Distillation for Fine-Grained GOOSE 2D Semantic Segmentation
We describe our 4th-place entry to the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which reached a composite mean Intersection-over-Union (mIoU) of 69.73% on the official 1,815-image test set. Our mo…
2D Semantic SegmentationUnsOcc: 3D Semantic Occupancy Prediction in Unstructured Scene via Rendering Fusion
Unstructured scenes present unique challenges for autonomous driving, as irregular obstacles and sparse scene layouts undermine the effectiveness of traditional perception methods such as 3D object detection. 3D semantic…
2D Semantic Segmentation3D Object DetectionAutonomous DrivingGeometric Flood Depth Estimation: Fusing Transformer-Based Segmentation with Digital Elevation Models
Post-disaster situational awareness relies heavily on understanding both the extent and the volume of floodwaters. While 2D semantic segmentation provides accurate flood masking, it lacks the vertical dimension required …
2D Semantic SegmentationDepth EstimationCross-Attentive Multiview Fusion of Vision-Language Embeddings
Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically…
2D Semantic SegmentationSpaceSense-Bench: A Large-Scale Multi-Modal Benchmark for Spacecraft Perception and Pose Estimation
Autonomous space operations such as on-orbit servicing and active debris removal demand robust part-level semantic understanding and precise relative navigation of target spacecraft, yet collecting large-scale real data …
Monocular Depth EstimationPoint Cloud Segmentation2D Semantic SegmentationObject DetectionXD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation
Until open-world foundation models match the performance of specialized approaches, deep learning systems remain dependent on task- and sensor-specific data availability. To bridge the gap between available datasets and …
2D Semantic Segmentation2D Panoptic Segmentation3D Semantic SegmentationDomain AdaptationSegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images
Most existing methods for training-free open-vocabulary semantic segmentation are based on CLIP. While these approaches have made progress, they often face challenges in precise localization or require complex pipelines …
3D Semantic Segmentation2D Semantic SegmentationChange DetectionMLPerf Automotive
We present MLPerf Automotive, the first standardized public benchmark for evaluating Machine Learning systems that are deployed for AI acceleration in automotive systems. Developed through a collaborative partnership bet…
2D Semantic Segmentation2D Object Detection3D Object DetectionRangeSAM: On the Potential of Visual Foundation Models for Range-View represented LiDAR segmentation
Point cloud segmentation is central to autonomous driving and 3D scene understanding. While voxel- and point-based methods dominate recent research due to their compatibility with deep architectures and ability to captur…
Point Cloud Segmentation2D Semantic SegmentationScene UnderstandingAutonomous DrivingNovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
Artificial Intelligence (AI) is accelerating the transformation of scientific research paradigms, not only enhancing research efficiency but also driving innovation. We introduce NovelSeek, a unified closed-loop multi-ag…
2D Semantic SegmentationActivity PredictionSemantic SegmentationTechnical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average
We report on the application of a high-capacity semantic segmentation pipeline to the GOOSE 2D Semantic Segmentation Challenge for unstructured off-road environments. Using a FlashInternImage-B backbone together with a U…
2D Semantic SegmentationDecoderRoad SegmentationSegmentation+1Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding
This report presents our semantic segmentation framework developed by team ACVLAB for the ICRA 2025 GOOSE 2D Semantic Segmentation Challenge, which focuses on parsing outdoor scenes into nine semantic categories under re…
2D Semantic SegmentationDenoisingScene UnderstandingSegmentation+1CaRaFFusion: Improving 2D Semantic Segmentation with Camera-Radar Point Cloud Fusion and Zero-Shot Image Inpainting
Segmenting objects in an environment is a crucial task for autonomous driving and robotics, as it enables a better understanding of the surroundings of each agent. Although camera sensors provide rich visual details, the…
2D Semantic SegmentationAutonomous DrivingImage InpaintingSemantic Segmentation3D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentation
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of…
2D Semantic Segmentation3D Semantic SegmentationAutonomous DrivingDomain Adaptation+4Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion
Identifying biomarkers in medical images is vital for a wide range of biotech applications. However, recent Transformer and CNN based methods often struggle with variations in morphology and staining, which limits their …
2D Semantic SegmentationImage SegmentationMedical Image SegmentationSemantic SegmentationCoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving
Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic…
2D Semantic Segmentation4D reconstructionAutonomous DrivingNovel View Synthesis+1RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation
Bird's Eye View (BEV) semantic maps have recently garnered a lot of attention as a useful representation of the environment to tackle assisted and autonomous driving tasks. However, most of the existing work focuses on t…
2D Semantic SegmentationAutonomous DrivingNovel View SynthesisSegmentation+1Few-shot Semantic Learning for Robust Multi-Biome 3D Semantic Mapping in Off-Road Environments
Off-road environments pose significant perception challenges for high-speed autonomous navigation due to unstructured terrain, degraded sensing conditions, and domain-shifts among biomes. Learning semantic information ac…
2D Semantic SegmentationAutonomous NavigationSegmentationSemantic SegmentationMOSE: Monocular Semantic Reconstruction Using NeRF-Lifted Noisy Priors
Accurately reconstructing dense and semantically annotated 3D meshes from monocular images remains a challenging task due to the lack of geometry guidance and imperfect view-dependent 2D priors. Though we have witnessed …
2D Semantic Segmentation3D Semantic SegmentationNeRFScene Understanding+22D Semantic-Guided Semantic Scene Completion
Semantic scene completion (SSC) aims to simultaneously perform scene completion (SC) and predict semantic categories of a 3D scene from a single depth and/or RGB image. Most existing SSC methods struggle to handle compl…
2D Semantic Segmentation3D Semantic Scene CompletionMissing ValuesSemantic Segmentation