From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment

• URL: http://arxiv.org/abs/2609.07346v1
• Date: Mon, 07 Sep 2026 11:09:30 GMT
• Title: From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment
• Abstract summary: SCODA is a lightweight scene-conditioned objective perceptual quality assessment method.<n>It shifts QA from explicit image-to-image comparison to scene-manifold modeling.<n> Experiments show strong agreement with human judgments and robust generalization across GS- and NeRF-generated views and trajectories.
• Score: 6.557590493848202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Radiance field representations such as 3D Gaussian Splatting (3DGS) enable high-quality novel view synthesis but can introduce complex, view-dependent artifacts from reconstruction, rendering, and compression. Reliable perceptual quality assessment (QA) is thus essential for evaluating rendered views and guiding the design of perceptually faithful scene representations. Existing full-reference QA metrics require an aligned reference image, while recent cross-reference metrics relax this requirement by comparing a test view with non-aligned references. However, under wide-baseline radiance field settings, selecting a reliable nearby reference can be difficult, particularly when evaluating views along arbitrary trajectories and poses. We propose SCODA, a lightweight scene-conditioned objective QA method that shifts QA from explicit image-to-image comparison to scene-manifold modeling. High-quality observations of each scene are represented as a multivariate Gaussian distribution in deep feature space, producing a semantic fidelity score that measures deviation from the scene distribution. A weakly-supervised distortion-aware patch discriminator provides a complementary realism signal, and both cues are combined through an unsupervised bounded fusion strategy. Experiments on multiple benchmarks show strong agreement with human judgments and robust generalization across GS- and NeRF-generated views and trajectories. Code is publicly available at https://gitlab.com/saeedmp/scoda.

Related papers

• SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding [15.452474276231799]
  SeqAlign3DVG is a novel benchmark dedicated to temporally ordered and strictly observation-aligned image-based 3D visual grounding.<n>It comprises 9,622 single-view and 14,493 sequence samples featuring rich descriptions, complex relations, and multi-instance ambiguities.<n>Our approach achieves state-of-the-art performance under the depth-free protocol, significantly improving localization for targets defined by complex relations and appearance cues.
  arXiv  Detail & Related papers  (2026-08-31T08:38:29Z)
• VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence [26.0945130521806]
  Existing benchmarks assess either textual answer correctness or pixel-level localization in isolation.<n>We introduce VISTAQA, a benchmark for joint evaluation of free-form answer correctness and pixel-level evidence grounding in visual question answering.<n>We introduce GROVE, a metric that enforces joint correctness by combining textual accuracy and grounding quality via a per-sample geometric mean.
  arXiv  Detail & Related papers  (2026-05-20T03:44:06Z)
• PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis [9.367653098793296]
  We propose a framework that evaluates diffusion-generated views using reference images from different poses.<n>PR-IQA achieves full-reference-level accuracy without ground-truth supervision.<n>Our quality-aware 3DGS approach more effectively filters inconsistencies, producing superior 3D reconstructions and NVS results.
  arXiv  Detail & Related papers  (2026-04-06T10:17:41Z)
• SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation [62.55421542903781]
  We present textbfSpatialReward, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images.<n>Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality.
  arXiv  Detail & Related papers  (2026-03-23T17:26:35Z)
• Beyond Frequency: Scoring-Driven Debiasing for Object Detection via Blueprint-Prompted Image Synthesis [97.37770785712475]
  We present a generation-based debiasing framework for object detection.<n>Our method significantly narrows the performance gap for underrepresented object groups.
  arXiv  Detail & Related papers  (2025-10-21T02:19:12Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• Loc$^2$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching [80.57282092735991]
  We propose an accurate and interpretable fine-grained cross-view localization method.<n>It estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image.<n> Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation.
  arXiv  Detail & Related papers  (2025-09-11T18:52:16Z)
• Hierarchical Scoring with 3D Gaussian Splatting for Instance Image-Goal Navigation [27.040017548286812]
  Instance Image-Goal Navigation (IIN) requires autonomous agents to identify and navigate to a target object or location depicted in a reference image captured from any viewpoint.<n>We introduce a novel IIN framework with a hierarchical scoring paradigm that estimates optimal viewpoints for target matching.
  arXiv  Detail & Related papers  (2025-06-09T00:58:14Z)
• UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image [86.7128543480229]
  Unseen object pose estimation methods often rely on CAD models or multiple reference views.<n>To simplify reference acquisition, we aim to estimate the unseen object's pose through a single unposed RGB-D reference image.<n>We present a novel approach and benchmark, termed UNOPose, for unseen one-reference-based object pose estimation.
  arXiv  Detail & Related papers  (2024-11-25T05:36:00Z)
• PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting [54.7468067660037]
  PF3plat sets a new state-of-the-art across all benchmarks, supported by comprehensive ablation studies validating our design choices.<n>Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-29T15:28:15Z)

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.