Novel View Synthesis

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

24 leaderboard tables shown for this task, 24 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 24 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

46 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 46 until expanded.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 579 papers with code (1,441 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
  19 Mar 2020 37 repositories listed Syntology ran 22 of 56 samples · 34 unverified · 4 pointer-only (licence)
  Our algorithm represents a scene using a fully-connected (non-convolutional) deep network, whose input is a single continuous 5D coordinate (spatial location (x, y, z) and viewing direction (θ, ϕ)) and whose output is…
• Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
  16 Jan 2022 17 repositories listed Syntology ran 18 of 44 samples · 26 unverified · 9 pointer-only (licence)
  Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate.
• NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
  20 Jun 2021 7 repositories listed Syntology ran 8 of 16 samples · 8 unverified
  In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation.
• PlenOctrees for Real-time Rendering of Neural Radiance Fields
  25 Mar 2021 5 repositories listed Syntology ran 6 of 13 samples · 7 unverified
  We introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects.
• NeRF--: Neural Radiance Fields Without Known Camera Parameters
  14 Feb 2021 5 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or…
• Deferred Neural Rendering: Image Synthesis using Neural Textures
  28 Apr 2019 4 repositories listed
  Similar to traditional textures, neural textures are stored as maps on top of 3D mesh proxies; however, the high-dimensional feature maps contain significantly more information, which can be interpreted by our new…
• View Synthesis by Appearance Flow
  11 May 2016 4 repositories listed
  We address the problem of novel view synthesis: given an input image, synthesizing new images of the same object or scene observed from arbitrary viewpoints.
• Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction
  28 Nov 2024 3 repositories listed Syntology ran 2 of 17 samples · 15 unverified
  We present DiffVox, a self-supervised framework for Cone-Beam Computed Tomography (CBCT) reconstruction by directly optimizing a voxelgrid representation using physics-based differentiable X-ray rendering.
• LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model
  19 May 2023 3 repositories listed
  As an exemplar, we leverage LeftRefill to address two different challenges: reference-guided inpainting and novel view synthesis, based on the pre-trained StableDiffusion.
• Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans
  31 Dec 2020 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh, so that…
• SynSin: End-to-end View Synthesis from a Single Image
  18 Dec 2019 3 repositories listed
  Single image view synthesis allows for the generation of new views of a scene given a single input image.
• HoloGAN: Unsupervised learning of 3D representations from natural images
  2 Apr 2019 3 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  This shows that HoloGAN is the first generative model that learns 3D representations from natural images in an entirely unsupervised manner.
• X-Field: A Physically Grounded Representation for 3D X-ray Reconstruction
  11 Mar 2025 2 repositories listed
  X-ray imaging is indispensable in medical diagnostics, yet its use is tightly regulated due to potential health risks.
• HAC++: Towards 100X Compression of 3D Gaussian Splatting
  21 Jan 2025 2 repositories listed
  3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity.
• CrossModalityDiffusion: Multi-Modal Novel View Synthesis with Unified Intermediate Representation
  16 Jan 2025 2 repositories listed
  The rendered feature images are used as conditioning inputs for a modality-specific diffusion model, enabling the synthesis of novel images for the desired output modality.
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes
  1 Nov 2024 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis.
• UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images
  17 Oct 2024 2 repositories listed
  Moreover, since the number of 3D Gaussians used as decoder queries is independent of the number of input views, our method allows arbitrary number of multi-view images as input without causing memory explosion or…
• DepthSplat: Connecting Gaussian Splatting and Depth
  17 Oct 2024 2 repositories listed Syntology ran 8 of 16 samples · 8 unverified
  Gaussian splatting and single/multi-view depth estimation are typically studied in isolation.
• Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
  10 Jun 2024 2 repositories listed
  Volumetric rendering based methods, like NeRF, excel in HDR view synthesis from RAWimages, especially for nighttime scenes.
• Multi-style Neural Radiance Field with AdaIN
  7 Jun 2024 2 repositories listed
  In this work, we propose a novel pipeline that combines AdaIN and NeRF for the task of stylized Novel View Synthesis.
• HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
  24 May 2024 2 repositories listed Syntology ran 5 of 7 samples · 2 unverified
  In this paper, we propose a new framework, High Dynamic Range Gaussian Splatting (HDR-GS), which can efficiently render novel HDR views and reconstruct LDR images with a user input exposure time.
• Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
  16 Apr 2024 2 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  Recently, 3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results, while allowing the rendering of high-resolution images in real-time.
• CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians
  1 Apr 2024 2 repositories listed
  The advancement of real-time 3D scene reconstruction and novel view synthesis has been significantly propelled by 3D Gaussian Splatting (3DGS).
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
  26 Mar 2024 2 repositories listed Syntology ran 6 of 10 samples · 4 unverified · 10 pointer-only (licence)
  3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking.
• HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression
  21 Mar 2024 2 repositories listed
  3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity.
• Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis
  7 Mar 2024 2 repositories listed Syntology ran 6 of 8 samples · 2 unverified · 8 pointer-only (licence)
  X-ray is widely applied for transmission imaging due to its stronger penetration than natural light.
• GPAvatar: Generalizable and Precise Head Avatar from Image(s)
  18 Jan 2024 2 repositories listed Syntology ran 8 of 10 samples · 2 unverified
  Head avatar reconstruction, crucial for applications in virtual reality, online meetings, gaming, and film industries, has garnered substantial attention within the computer vision community.
• Compact 3D Scene Representation via Self-Organizing Gaussian Grids
  19 Dec 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  In this paper, we introduce a compact scene representation organizing the parameters of 3D Gaussian Splatting (3DGS) into a 2D grid with local homogeneity, ensuring a drastic reduction in storage requirements without…
• TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces
  15 Dec 2023 2 repositories listed Syntology ran 8 of 11 samples · 3 unverified
  This report describes the solution that secured the first place in the "View Synthesis Challenge for Human Heads (VSCHH)" at the ICCV 2023 workshop.
• Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
  6 Dec 2023 2 repositories listed Syntology ran 12 of 24 samples · 12 unverified · 1 pointer-only (licence)
  In this work, we go one step further: in addition to radiance field rendering, we enable 3D Gaussian splatting on arbitrary-dimension semantic features via 2D foundation model distillation.

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.