Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2605.05155v1
• Date: Wed, 06 May 2026 17:27:09 GMT
• Title: Aes3D: Aesthetic Assessment in 3D Gaussian Splatting
• Abstract summary: Aes3D is the first systematic framework for assessing the aesthetics of 3D neural rendering scenes.<n>Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment.<n>Aes3DGSNet is a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations.
• Score: 14.297200222005918
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-level primitive representation, which makes it difficult to capture high-level aesthetic features. To address these challenges, we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment, built on our proposed annotation strategy for 3D scene aesthetics. In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations. Notably, our model operates solely on 3D Gaussian primitives, eliminating the need for rendering multi-view images and thus reducing computational cost and hardware requirements. Through aesthetics-supervised learning on multi-view 3DGS scene representations, Aes3DGSNet effectively captures high-level aesthetic cues and accurately regresses aesthetic scores. Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment. Code and datasets will be made available in a future version.

Related papers

• EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation [92.9295124221522]
  EPS3D is an end-to-end feed-forward framework for open-vocabulary 3D panoptic segmentation.<n>It predicts semantic and instance features from multi-view images, improving 3D consistency and avoiding error accumulation.<n>It supports tasks like robotic manipulation and 3D scene editing.
  arXiv  Detail & Related papers  (2026-06-08T03:26:54Z)
• LabelAny3D: Label Any Object 3D in the Wild [18.044792932630752]
  COCO3D is a new benchmark for open-vocabulary monocular 3D detection, derived from the MS-COCO dataset.<n>We introduce LabelAny3D, an emphanalysis-by-synthesis framework that reconstructs holistic 3D scenes from 2D images to efficiently produce high-quality 3D bounding box annotations.
  arXiv  Detail & Related papers  (2026-01-04T22:03:45Z)
• Towards Physically Executable 3D Gaussian for Embodied Navigation [37.428618598143395]
  SAGE-3D is a new paradigm that upgrades 3DGS into an executable, semantically and physically aligned environment.<n>It comprises two components: (1) Object-Centric Semantic Grounding, which adds object-level fine-grained annotations to 3DGS; and (2) Physics-Aware Execution Jointing, which embeds collision objects into 3DGS.<n>We release InteriorGS, containing 1K object-annotated 3DGS indoor scene data, and introduce SAGE-Bench, the first 3DGS-based VLN benchmark with 2M VLN data.
  arXiv  Detail & Related papers  (2025-10-24T10:05:00Z)
• Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity [78.7107376451476]
  Hi3DEval is a hierarchical evaluation framework tailored for 3D generative content.<n>We extend texture evaluation beyond aesthetic appearance by explicitly assessing material realism.<n>We propose a 3D-aware automated scoring system based on hybrid 3D representations.
  arXiv  Detail & Related papers  (2025-08-07T17:50:13Z)
• Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning [63.94919846010485]
  3D Gaussian inpainting (3DGI) is challenging in effectively leveraging complementary visual and semantic cues from multiple input views.<n>We propose a method that measures the visibility uncertainties of 3D points across different input views and uses them to guide 3DGI.<n>We build a novel 3DGI framework, VISTA, by integrating VISibility-uncerTainty-guided 3DGI with scene conceptuAl learning.
  arXiv  Detail & Related papers  (2025-04-23T06:21:11Z)
• Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness [73.72335146374543]
  We introduce reconstructive visual instruction tuning with 3D-awareness (Ross3D), which integrates 3D-aware visual supervision into the training procedure.<n>Ross3D achieves state-of-the-art performance across various 3D scene understanding benchmarks.
  arXiv  Detail & Related papers  (2025-04-02T16:59:55Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [111.16358607889609]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation.<n>For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)
• CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes [68.61199623705096]
  We design a novel 3D pre-training Vision-Language method that helps a model learn semantically meaningful and transferable 3D scene point cloud representations. We inject the representational power of the popular CLIP model into our 3D encoder by aligning the encoded 3D scene features with the corresponding 2D image and text embeddings. We evaluate our model's 3D world reasoning capability on the downstream task of 3D Visual Question Answering.
  arXiv  Detail & Related papers  (2023-04-12T16:52:29Z)
• Learning 3D Scene Priors with 2D Supervision [37.79852635415233]
  We propose a new method to learn 3D scene priors of layout and shape without requiring any 3D ground truth. Our method represents a 3D scene as a latent vector, from which we can progressively decode to a sequence of objects characterized by their class categories. Experiments on 3D-FRONT and ScanNet show that our method outperforms state of the art in single-view reconstruction.
  arXiv  Detail & Related papers  (2022-11-25T15:03:32Z)

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.