AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark

• URL: http://arxiv.org/abs/2409.15041v1
• Date: Mon, 23 Sep 2024 14:10:06 GMT
• Title: AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark
• Authors: Michal Nazarczuk, Thomas Tanay, Sibi Catley-Chandar, Richard Shaw, Radu Timofte, Eduardo Pérez-Pellitero,
• Abstract summary: Differentiable rendering relies on a dense viewpoint coverage of the scene. Many challenges arise when only a few input views are available. A recurring problem in sparse rendering literature is the lack of an homogeneous, up-to-date, dataset and evaluation protocol. We introduce a new dataset that follows the setup of the DTU MVS dataset.
• Score: 43.76981659253837
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent developments in differentiable and neural rendering have made impressive breakthroughs in a variety of 2D and 3D tasks, e.g. novel view synthesis, 3D reconstruction. Typically, differentiable rendering relies on a dense viewpoint coverage of the scene, such that the geometry can be disambiguated from appearance observations alone. Several challenges arise when only a few input views are available, often referred to as sparse or few-shot neural rendering. As this is an underconstrained problem, most existing approaches introduce the use of regularisation, together with a diversity of learnt and hand-crafted priors. A recurring problem in sparse rendering literature is the lack of an homogeneous, up-to-date, dataset and evaluation protocol. While high-resolution datasets are standard in dense reconstruction literature, sparse rendering methods often evaluate with low-resolution images. Additionally, data splits are inconsistent across different manuscripts, and testing ground-truth images are often publicly available, which may lead to over-fitting. In this work, we propose the Sparse Rendering (SpaRe) dataset and benchmark. We introduce a new dataset that follows the setup of the DTU MVS dataset. The dataset is composed of 97 new scenes based on synthetic, high-quality assets. Each scene has up to 64 camera views and 7 lighting configurations, rendered at 1600x1200 resolution. We release a training split of 82 scenes to foster generalizable approaches, and provide an online evaluation platform for the validation and test sets, whose ground-truth images remain hidden. We propose two different sparse configurations (3 and 9 input images respectively). This provides a powerful and convenient tool for reproducible evaluation, and enable researchers easy access to a public leaderboard with the state-of-the-art performance scores. Available at: https://sparebenchmark.github.io/

Related papers

• FlowR: Flowing from Sparse to Dense 3D Reconstructions [60.6368083163258]
  We propose a flow matching model that learns a flow to connect novel view renderings to renderings that we expect from dense reconstructions. Our model is trained on a novel dataset of 3.6M image pairs and can process up to 45 views at 540x960 resolution (91K tokens) on one H100 GPU in a single forward pass.
  arXiv  Detail & Related papers  (2025-04-02T11:57:01Z)
• Para-Lane: Multi-Lane Dataset Registering Parallel Scans for Benchmarking Novel View Synthesis [5.281171924360707]
  We present the first multi-lane dataset registering parallel scans for novel driving view dataset derived from real-world scans. The dataset consists of 25 groups of associated sequences, including 16,000 front-view images, 64,000 surround-view images, and 16,000 LiDAR frames. We evaluate the performance of existing approaches in various testing scenarios at different lanes and distances.
  arXiv  Detail & Related papers  (2025-02-21T18:03:56Z)
• MegaScenes: Scene-Level View Synthesis at Scale [69.21293001231993]
  Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. We create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. We analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency.
  arXiv  Detail & Related papers  (2024-06-17T17:55:55Z)
• Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction [51.3632308129838]
  We present Total-Decom, a novel method for decomposed 3D reconstruction with minimal human interaction. Our approach seamlessly integrates the Segment Anything Model (SAM) with hybrid implicit-explicit neural surface representations and a mesh-based region-growing technique for accurate 3D object decomposition. We extensively evaluate our method on benchmark datasets and demonstrate its potential for downstream applications, such as animation and scene editing.
  arXiv  Detail & Related papers  (2024-03-28T11:12:33Z)
• DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering [126.00165445599764]
  We present DNA-Rendering, a large-scale, high-fidelity repository of human performance data for neural actor rendering. Our dataset contains over 1500 human subjects, 5000 motion sequences, and 67.5M frames' data volume. We construct a professional multi-view system to capture data, which contains 60 synchronous cameras with max 4096 x 3000 resolution, 15 fps speed, and stern camera calibration steps.
  arXiv  Detail & Related papers  (2023-07-19T17:58:03Z)
• SIDAR: Synthetic Image Dataset for Alignment & Restoration [2.9649783577150837]
  There is a lack of datasets that provide enough data to train and evaluate end-to-end deep learning models. Our proposed data augmentation helps to overcome the issue of data scarcity by using 3D rendering. The resulting dataset can serve as a training and evaluation set for a multitude of tasks involving image alignment and artifact removal.
  arXiv  Detail & Related papers  (2023-05-19T23:32:06Z)
• Fast Non-Rigid Radiance Fields from Monocularized Data [66.74229489512683]
  This paper proposes a new method for full 360deg inward-facing novel view synthesis of non-rigidly deforming scenes. At the core of our method are 1) An efficient deformation module that decouples the processing of spatial and temporal information for accelerated training and inference; and 2) A static module representing the canonical scene as a fast hash-encoded neural radiance field. In both cases, our method is significantly faster than previous methods, converging in less than 7 minutes and achieving real-time framerates at 1K resolution, while obtaining a higher visual accuracy for generated novel views.
  arXiv  Detail & Related papers  (2022-12-02T18:51:10Z)
• Learning Dynamic View Synthesis With Few RGBD Cameras [60.36357774688289]
  We propose to utilize RGBD cameras to synthesize free-viewpoint videos of dynamic indoor scenes. We generate point clouds from RGBD frames and then render them into free-viewpoint videos via a neural feature. We introduce a simple Regional Depth-Inpainting module that adaptively inpaints missing depth values to render complete novel views.
  arXiv  Detail & Related papers  (2022-04-22T03:17:35Z)
• ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation [23.767094632640763]
  We present ClevrTex, designed as the next challenge to compare, evaluate and analyze algorithms. ClarTex features synthetic scenes with diverse shapes, textures and photo-mapped materials, created using physically based rendering techniques. We benchmark a large set of recent unsupervised multi-object segmentation models on ClevrTex and find all state-of-the-art approaches fail to learn good representations in the textured setting.
  arXiv  Detail & Related papers  (2021-11-19T15:11:25Z)
• SVIRO: Synthetic Vehicle Interior Rear Seat Occupancy Dataset and Benchmark [11.101588888002045]
  We release SVIRO, a synthetic dataset for sceneries in the passenger compartment of ten different vehicles. We analyze machine learning-based approaches for their generalization capacities and reliability when trained on a limited number of variations.
  arXiv  Detail & Related papers  (2020-01-10T14:44:23Z)

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.