WHU-Infra3D is a new large-scale multi-modal dataset and benchmark for 3D roadside infrastructure inventory, providing over 175k 2D boxes, thousands of 3D instances, and 181k annotations across five core tasks while exposing cross-city gaps and long-tailed defect vulnerabilities.
org/abs/2411.14347
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
abstract
In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level representation for open-world object understanding. To make long-tailed object detection easy, DINO-X extends its input options to support text prompt, visual prompt, and customized prompt. With such flexible prompt options, we develop a universal object prompt to support prompt-free open-world detection, making it possible to detect anything in an image without requiring users to provide any prompt. To enhance the model's core grounding capability, we have constructed a large-scale dataset with over 100 million high-quality grounding samples, referred to as Grounding-100M, for advancing the model's open-vocabulary detection performance. Pre-training on such a large-scale grounding dataset leads to a foundational object-level representation, which enables DINO-X to integrate multiple perception heads to simultaneously support multiple object perception and understanding tasks, including detection, segmentation, pose estimation, object captioning, object-based QA, etc. Experimental results demonstrate the superior performance of DINO-X. Specifically, the DINO-X Pro model achieves 56.0 AP, 59.8 AP, and 52.4 AP on the COCO, LVIS-minival, and LVIS-val zero-shot object detection benchmarks, respectively. Notably, it scores 63.3 AP and 56.5 AP on the rare classes of LVIS-minival and LVIS-val benchmarks, improving the previous SOTA performance by 5.8 AP and 5.0 AP. Such a result underscores its significantly improved capacity for recognizing long-tailed objects.
representative citing papers
VASA is a vision-guided agent for open ad-hoc segmentation that creates and validates masks through planning, tool use, and error recovery, outperforming baselines on the new PARS benchmark and RefCOCOm.
An image generator is instruction-tuned to perform diverse vision tasks by representing task outputs as RGB images, achieving SOTA on segmentation and depth estimation.
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
HEE is a training-free, model-agnostic method for high-resolution visual perception in MLLMs using hierarchical entity exploration with dual scoring, detection, clustering, and backtracking.
DroneFINE is a domain-aware PEFT approach for VLM-based drone detectors using foreground-aware multi-path adaptation and text-conditioned background suppression, outperforming standard PEFT and matching full fine-tuning on VisDrone and UAVDT with fewer trainable parameters.
ShotCrop uses three-stage training (CoT SFT, pseudo-label semi-supervised, GRPO-S) to produce triple-shot compositions and reports 2.82x better shot localization than GPT-5 on a 1.2k expert benchmark.
SceneParser introduces hierarchical scene parsing as object-part-affordance chains, a VLM trained with pseudo labels and curriculum learning, and SceneParser-Bench with 1.74M affordance annotations, showing better structure-aware results than existing MLLMs.
DeFacto trains multimodal models with counterfactual image variants and GRPO reinforcement learning to enforce that correct answers are supported by correct visual evidence.
VL-DINO improves open-vocabulary object detection by adding QPSC, VSE, and ORSA modules that inject CLIP knowledge into DINO, reaching 36.3 and 38.1 AP zero-shot on LVIS.
COAL combines VLM-based explicit semantic injection and LLM-driven counterfactual learning inside a hierarchical architecture to improve discriminative referring multi-object tracking under sparse supervision.
See&Say combines depth gradients, semantic masks, and VLM-guided refinement to generate safety maps and alternative drop zones for autonomous drone deliveries, outperforming baselines in accuracy and IoU.
VocaDet detects arbitrary objects by retrieving multi-granularity visual tokens from a sample-built vector database of position-debiased DINOv3 features and topology, without detector training.
citing papers explorer
-
WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory
WHU-Infra3D is a new large-scale multi-modal dataset and benchmark for 3D roadside infrastructure inventory, providing over 175k 2D boxes, thousands of 3D instances, and 181k annotations across five core tasks while exposing cross-city gaps and long-tailed defect vulnerabilities.
-
Vision Harnessing Agent for Open Ad-hoc Segmentation
VASA is a vision-guided agent for open ad-hoc segmentation that creates and validates masks through planning, tool use, and error recovery, outperforming baselines on the new PARS benchmark and RefCOCOm.
-
Image Generators are Generalist Vision Learners
An image generator is instruction-tuned to perform diverse vision tasks by representing task outputs as RGB images, achieving SOTA on segmentation and depth estimation.
-
SAM 3: Segment Anything with Concepts
SAM 3 introduces promptable concept segmentation that doubles accuracy of prior systems on images and videos while improving standard SAM segmentation performance.
-
Towards High-Resolution Visual Perception via Hierarchical Entity Exploration
HEE is a training-free, model-agnostic method for high-resolution visual perception in MLLMs using hierarchical entity exploration with dual scoring, detection, clustering, and backtracking.
-
DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
DroneFINE is a domain-aware PEFT approach for VLM-based drone detectors using foreground-aware multi-path adaptation and text-conditioned background suppression, outperforming standard PEFT and matching full fine-tuning on VisDrone and UAVDT with fewer trainable parameters.
-
ShotCrop$^3$: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions
ShotCrop uses three-stage training (CoT SFT, pseudo-label semi-supervised, GRPO-S) to produce triple-shot compositions and reports 2.82x better shot localization than GPT-5 on a 1.2k expert benchmark.
-
SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding
SceneParser introduces hierarchical scene parsing as object-part-affordance chains, a VLM trained with pseudo labels and curriculum learning, and SceneParser-Bench with 1.74M affordance annotations, showing better structure-aware results than existing MLLMs.
-
DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
DeFacto trains multimodal models with counterfactual image variants and GRPO reinforcement learning to enforce that correct answers are supported by correct visual evidence.
-
VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio
VL-DINO improves open-vocabulary object detection by adding QPSC, VSE, and ORSA modules that inject CLIP knowledge into DINO, reaching 36.3 and 38.1 AP zero-shot on LVIS.
-
COAL: Counterfactual and Observation-Enhanced Alignment Learning for Discriminative Referring Multi-Object Tracking
COAL combines VLM-based explicit semantic injection and LLM-driven counterfactual learning inside a hierarchical architecture to improve discriminative referring multi-object tracking under sparse supervision.
-
See&Say: Vision Language Guided Safe Zone Detection for Autonomous Package Delivery Drones
See&Say combines depth gradients, semantic masks, and VLM-guided refinement to generate safety maps and alternative drop zones for autonomous drone deliveries, outperforming baselines in accuracy and IoU.
-
VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval
VocaDet detects arbitrary objects by retrieving multi-granularity visual tokens from a sample-built vector database of position-debiased DINOv3 features and topology, without detector training.