E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes

• URL: http://arxiv.org/abs/2604.17969v2
• Date: Thu, 23 Apr 2026 06:55:57 GMT
• Title: E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes
• Abstract summary: E3VS-Bench is a benchmark for embodied 3D visual search in real-world 3D environments.<n>It consists of 99 high-fidelity 3D scenes reconstructed using 3D Gaussian Splatting and 2,014 question-driven episodes.<n>We evaluate multiple state-of-the-art VLMs and compare their performance with humans.
• Score: 42.5758395227096
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual search in 3D environments requires embodied agents to actively explore their surroundings and acquire task-relevant evidence. However, existing visual search and embodied AI benchmarks, including EQA, typically rely on static observations or constrained egocentric motion, and thus do not explicitly evaluate fine-grained viewpoint-dependent phenomena that arise under unrestricted 5-DoF viewpoint control in real-world 3D environments, such as visibility changes caused by vertical viewpoint shifts, revealing contents inside containers, and disambiguating object attributes that are only observable from specific angles. To address this limitation, we introduce {E3VS-Bench}, a benchmark for embodied 3D visual search where agents must control their viewpoints in 5-DoF to gather viewpoint-dependent evidence for question answering. E3VS-Bench consists of 99 high-fidelity 3D scenes reconstructed using 3D Gaussian Splatting and 2,014 question-driven episodes. 3D Gaussian Splatting enables photorealistic free-viewpoint rendering that preserves fine-grained visual details (e.g., small text and subtle attributes) often degraded in mesh-based simulators, thereby allowing the construction of questions that cannot be answered from a single view and instead require active inspection across viewpoints in 5-DoF. We evaluate multiple state-of-the-art VLMs and compare their performance with humans. Despite strong 2D reasoning ability, all models exhibit a substantial gap from humans, highlighting limitations in active perception and coherent viewpoint planning specifically under full 5-DoF viewpoint changes.

Related papers

• SceneBench: A Hierarchical Benchmark for Vision-Language Understanding of 3D Scenes [12.672496253081258]
  Vision-language models excel at 2D image understanding but remain limited in 3D spatial reasoning.<n>We introduce SceneBench, a benchmark of 966 photorealistic 3D scenes reconstructed with Gaussian Splatting.<n>SceneBench provides a realistic testbed for developing and evaluating models capable of fine-grained spatial reasoning.
  arXiv  Detail & Related papers  (2026-09-14T18:59:13Z)
• VR3D: View-Robust 3D Representation Learning for Aerial-Ground Person Re-Identification [35.655590576867574]
  Aerial-ground person re-identification is a challenging task due to cross-platform viewpoint variations.<n>Existing methods attempt to learn view-invariant representations exclusively within the 2D image space.<n>We propose VR3D, a View-Robust 3D Representation Learning framework that maps images into a unified 3D coordinate space.
  arXiv  Detail & Related papers  (2026-08-03T17:59:01Z)
• AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models [0.0]
  3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions.<n>We present $bftextAgentGrounder$, a zero-shot 3D visual grounding framework that operates directly on colored point clouds without task-specific 3D training.
  arXiv  Detail & Related papers  (2026-05-25T14:29:04Z)
• Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds [57.024495128182195]
  We conduct a pilot study across different observation spaces and visual representations.<n>Results show that explicitly lifting visual input into point clouds yields representations that better complement their corresponding 2D representations.<n>We propose Any3D-VLA to address the challenges of (1) scarce 3D data and (2) the domain gap induced by cross-environment differences and depth-scale biases.
  arXiv  Detail & Related papers  (2026-01-31T16:34:52Z)
• Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation [54.04601077224252]
  Embodied scene understanding requires not only comprehending visual-spatial information but also determining where to explore next in the 3D physical world.<n>underlinetextbf3D vision-language learning enables embodied agents to effectively explore and understand their environment.<n>model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images.
  arXiv  Detail & Related papers  (2025-07-05T14:15:52Z)
• NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation [14.046423852723615]
  We introduce a novel 3D Gaussian Splatting based hard visual prompting approach to generate diverse viewpoints around target objects.<n>Our method simulates realistic 3D perspectives, effectively augmenting existing hard visual prompts.<n>This training-free strategy integrates seamlessly with prior hard visual prompts, enriching object-descriptive features.
  arXiv  Detail & Related papers  (2025-04-20T14:39:27Z)
• Volumetric Environment Representation for Vision-Language Navigation [66.04379819772764]
  Vision-language navigation (VLN) requires an agent to navigate through a 3D environment based on visual observations and natural language instructions. We introduce a Volumetric Environment Representation (VER), which voxelizes the physical world into structured 3D cells. VER predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly.
  arXiv  Detail & Related papers  (2024-03-21T06:14:46Z)
• HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting [53.6394928681237]
  holistic understanding of urban scenes based on RGB images is a challenging yet important problem. Our main idea involves the joint optimization of geometry, appearance, semantics, and motion using a combination of static and dynamic 3D Gaussians. Our approach offers the ability to render new viewpoints in real-time, yielding 2D and 3D semantic information with high accuracy.
  arXiv  Detail & Related papers  (2024-03-19T13:39:05Z)
• SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection [19.75965521357068]
  We propose a novel approach called SOGDet (Semantic-Occupancy Guided Multi-view 3D Object Detection) to improve the accuracy of 3D object detection. Our results show that SOGDet consistently enhance the performance of three baseline methods in terms of nuScenes Detection Score (NDS) and mean Average Precision (mAP) This indicates that the combination of 3D object detection and 3D semantic occupancy leads to a more comprehensive perception of the 3D environment, thereby aiding build more robust autonomous driving systems.
  arXiv  Detail & Related papers  (2023-08-26T07:38:21Z)
• 3D Concept Learning and Reasoning from Multi-View Images [96.3088005719963]
  We introduce a new large-scale benchmark for 3D multi-view visual question answering (3DMV-VQA) This dataset consists of approximately 5k scenes, 600k images, paired with 50k questions. We propose a novel 3D concept learning and reasoning framework that seamlessly combines neural fields, 2D pre-trained vision-language models, and neural reasoning operators.
  arXiv  Detail & Related papers  (2023-03-20T17:59:49Z)
• Neural Groundplans: Persistent Neural Scene Representations from a Single Image [90.04272671464238]
  We present a method to map 2D image observations of a scene to a persistent 3D scene representation. We propose conditional neural groundplans as persistent and memory-efficient scene representations.
  arXiv  Detail & Related papers  (2022-07-22T17:41:24Z)
• CoCoNets: Continuous Contrastive 3D Scene Representations [21.906643302668716]
  This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos. We show the resulting 3D visual feature representations effectively scale across objects and scenes, imagine information occluded or missing from the input viewpoints, track objects over time, align semantically related objects in 3D, and improve 3D object detection.
  arXiv  Detail & Related papers  (2021-04-08T15:50:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.