Bilateral Guided Radiance Field Processing

Have you ever captured a dataset only to realize that your camera was set to manual mode, causing exposure to fluctuate?

Have you ever captured a dataset only to realize that your camera was set to manual mode, causing exposure to fluctuate?

Michael Rubloff

Michael Rubloff

Michael is the Founder and Managing Editor of Radiancefields.com

Tags

Bilateral Guided Radiance Field Processing

Have you ever captured a dataset only to realize that your camera was set to manual mode, causing exposure to fluctuate? These inconsistencies can break the multi-view consistency crucial for Neural Radiance Fields (NeRF), resulting in degraded or failed reconstructions.

In my consulting work, a common question I encounter is about the ability to recolor or retouch images before processing the radiance field. Both of these issues are solved with Bilateral Guided Radiance Field Processing.

Not only can it handle fluctuating exposure levels, but you only need to edit a single image, and the method will propagate the style to the entire reconstruction. They also can handle HDR through their own pipeline that resembles the HDR+ algorithm, first merging a burst of frames and then applying local tone mapping for finishing.  

The first stage involves disentangling image signal processing (ISP) enhancements. The researchers introduce a differentiable 3D bilateral grid that acts as a locally affine model, capable of approximating the complex, non-linear operations performed by ISPs on each input view. This grid captures and models view-dependent ISP enhancements, such as exposure adjustments and color corrections, by optimizing the NeRF along with these grids.

By separating the ISP processing effects from NeRF training, the reconstructed radiance fields maintain multi-view consistency and are largely free from artifacts like floaters. This method handles featureless spaces, such as walls, quite adeptly. The bilateral grids are optimized during the training process to closely match the ISP effects for each view, effectively learning the unique enhancements applied by the camera.

Once the NeRF training with disentangled ISP effects is complete, the finishing stage reapplying and enhancing these adjustments consistently across the entire 3D scene. Although it sounds like something from a Mortal Kombat game, the finishing stage is crucial.

The researchers propose a novel low-rank 4D bilateral grid to lift 2D view edits to 3D space. This grid allows users to perform detailed retouching on a single view and have those adjustments propagated consistently across the entire 3D scene. The low-rank approximation ensures the grid remains computationally feasible while effectively capturing the essential transformations needed for consistent 3D editing. Additionally they found low rank is a good prior for high-dimensional tensor completion. This idea is borrowed from the "low-rank matrix completion problem".

Users can apply various enhancements, such as color correction and brightness adjustment, to a selected view using familiar 2D photo editing tools, such as Lightroom. Adobe's recent efforts to build out their 3D reconstruction pipeline make it easy to imagine a future where Lightroom and other Adobe products extend to hyper-real 3D!

This method lifts these 2D edits to the 3D radiance fields, ensuring that adjustments are uniformly applied across all views, including full 360-degree captures. Additionally, users can continue to make edits in 2D, which can then be applied to the NeRF without needing to retrain. Keep in mind that you will need to rerun the finishing stage. For instance, you can adjust the lighting of a scene or simply recolor an object. This fine-grain control using common photo editors is a significant advantage.

The method is built on top of a PyTorch implementation of Zip-NeRF and can run on a single 3090 GPU. The process takes about two and a quarter hours, though this duration is directly tied to the NeRF method used. Adapting it to Instant-NGP or Nerfacto could result in significant speed boosts. The finishing stage operates much faster, currently taking about 15 minutes to complete.

With the code already released under an Apache 2.0 License, allowing for a multitude of use cases, it won't be long before you can revisit your HDR captures that never worked before. NeRFs continue to evolve with no known ceiling, making the future bright for radiance field technologies.

For more information, check out their project page or catch them at SIGGRAPH in Denver this July, where they will be presenting.

Thumbnail for Gaussian Splatting News episode 12

11:38

Watch · New every Monday

Splats Come to Fortnite, Nike Shoots in 4D, Splats on a Nintendo 3DS

Episode 12 · Nov 9, 2026

Epic’s UEFN 43.00 brings Gaussian splats into the Unreal Editor for Fortnite, importing PLY and SPZ files that render on every platform UEFN supports, mobile included.

Featured

Recents

Platforms

sperid-swift-mlx Brings Idol Image-to-Splat to the Mac

sperid-swift-mlx ports Speri Labs' Idol to Swift and MLX, turning one photo into a 3D Gaussian splat on Apple Silicon Macs with PLY, USDZ, and GLB export.

Michael Rubloff

Nov 15, 2026

Platforms

sperid-swift-mlx Brings Idol Image-to-Splat to the Mac

sperid-swift-mlx ports Speri Labs' Idol to Swift and MLX, turning one photo into a 3D Gaussian splat on Apple Silicon Macs with PLY, USDZ, and GLB export.

Michael Rubloff

Platforms

LCC Studio Universal V2.7.0 Adds AMD and Intel GPU Support

XGRIDS LCC Studio Universal V2.7.0 brings single-scene 3DGS reconstruction, editing and application to AMD and Intel discrete GPUs, alongside its NVIDIA build.

Michael Rubloff

Nov 15, 2026

Platforms

LCC Studio Universal V2.7.0 Adds AMD and Intel GPU Support

XGRIDS LCC Studio Universal V2.7.0 brings single-scene 3DGS reconstruction, editing and application to AMD and Intel discrete GPUs, alongside its NVIDIA build.

Michael Rubloff

Platforms

ovrtx 0.7.0 Adds Diffuse Relighting for Gaussian Splats

NVIDIA ovrtx 0.7.0 lets Gaussian splats be relit by scene lights with a bundled MDL material and adds experimental lidar rendering of NuRec-trained splats.

Michael Rubloff

Nov 14, 2026

Platforms

ovrtx 0.7.0 Adds Diffuse Relighting for Gaussian Splats

NVIDIA ovrtx 0.7.0 lets Gaussian splats be relit by scene lights with a bundled MDL material and adds experimental lidar rendering of NuRec-trained splats.

Michael Rubloff

News

MPEG GS4 and GS5 Gaussian Splats Now Decode in the Browser

MPEG GS4 and GS5 Gaussian splat profiles now decode client-side in a browser demo, using WebAssembly reference decoders inside a SuperSplat-based player.

Michael Rubloff

Nov 14, 2026

News

MPEG GS4 and GS5 Gaussian Splats Now Decode in the Browser

MPEG GS4 and GS5 Gaussian splat profiles now decode client-side in a browser demo, using WebAssembly reference decoders inside a SuperSplat-based player.

Michael Rubloff

Trending Articles
  1. TRENDING
    Loading...
  2. TRENDING
    Loading...
  3. TRENDING
    Loading...
Michael Rubloff

Written by Michael Rubloff

Michael is the Founder and Managing Editor of Radiancefields.com

More from Michael Rubloff

More from Michael Rubloff

Platforms

sperid-swift-mlx Brings Idol Image-to-Splat to the Mac

sperid-swift-mlx ports Speri Labs' Idol to Swift and MLX, turning one photo into a 3D Gaussian splat on Apple Silicon Macs with PLY, USDZ, and GLB export.

Michael Rubloff

Nov 15, 2026

Sperid Idol

Platforms

sperid-swift-mlx Brings Idol Image-to-Splat to the Mac

Michael Rubloff

Nov 15, 2026

Sperid Idol

Platforms

sperid-swift-mlx Brings Idol Image-to-Splat to the Mac

sperid-swift-mlx ports Speri Labs' Idol to Swift and MLX, turning one photo into a 3D Gaussian splat on Apple Silicon Macs with PLY, USDZ, and GLB export.

Michael Rubloff

Nov 15, 2026

Sperid Idol

Platforms

LCC Studio Universal V2.7.0 Adds AMD and Intel GPU Support

XGRIDS LCC Studio Universal V2.7.0 brings single-scene 3DGS reconstruction, editing and application to AMD and Intel discrete GPUs, alongside its NVIDIA build.

Michael Rubloff

Nov 15, 2026

Platforms

LCC Studio Universal V2.7.0 Adds AMD and Intel GPU Support

Michael Rubloff

Nov 15, 2026

Platforms

LCC Studio Universal V2.7.0 Adds AMD and Intel GPU Support

XGRIDS LCC Studio Universal V2.7.0 brings single-scene 3DGS reconstruction, editing and application to AMD and Intel discrete GPUs, alongside its NVIDIA build.

Michael Rubloff

Nov 15, 2026

Platforms

ovrtx 0.7.0 Adds Diffuse Relighting for Gaussian Splats

NVIDIA ovrtx 0.7.0 lets Gaussian splats be relit by scene lights with a bundled MDL material and adds experimental lidar rendering of NuRec-trained splats.

Michael Rubloff

Nov 14, 2026

NVIDIA

Platforms

ovrtx 0.7.0 Adds Diffuse Relighting for Gaussian Splats

Michael Rubloff

Nov 14, 2026

NVIDIA

Platforms

ovrtx 0.7.0 Adds Diffuse Relighting for Gaussian Splats

NVIDIA ovrtx 0.7.0 lets Gaussian splats be relit by scene lights with a bundled MDL material and adds experimental lidar rendering of NuRec-trained splats.

Michael Rubloff

Nov 14, 2026

NVIDIA

New to Gaussian Splatting? Start here

Radiance fields, explained from the ground up: what a Gaussian splat is, how to capture one, and which tools and gear to start with.

Newsletter

Keep up with the field.

New research, tools and captures from the Radiance Fields newsroom, in your inbox. Free, no spam.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.