REVIEW 7 cited by
Learning to Predict Indoor Illumination from a Single Image
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene. In contrast to previous work that relies on specialized image capture, user input, and/or simple scene models, we train an end-to-end deep neural network that directly regresses a limited field-of-view photo to HDR illumination, without strong assumptions on scene geometry, material properties, or lighting. We show that this can be accomplished in a three step process: 1) we train a robust lighting classifier to automatically annotate the location of light sources in a large dataset of LDR environment maps, 2) we use these annotations to train a deep neural network that predicts the location of lights in a scene from a single limited field-of-view photo, and 3) we fine-tune this network using a small dataset of HDR environment maps to predict light intensities. This allows us to automatically recover high-quality HDR illumination estimates that significantly outperform previous state-of-the-art methods. Consequently, using our illumination estimates for applications like 3D object insertion, we can achieve results that are photo-realistic, which is validated via a perceptual user study.
Forward citations
Cited by 7 Pith papers
-
Generative Relightable Avatars
GRA combines UV-space material optimization and physics rendering with feed-forward texture refinement and a fine-tuned video-to-video diffusion model to achieve controllable, high-detail relighting of full-body avatars.
-
360Anything: Geometry-Free Lifting of Images and Videos to 360{\deg}
360Anything lifts perspective images and videos to 360° panoramas with a diffusion transformer and sequence concatenation, requiring no camera metadata at test time.
-
LuxDiT: Lighting Estimation with Video Diffusion Transformer
A video diffusion transformer fine-tuned on synthetic and real data predicts HDR environment maps from images/videos, cutting peak light-direction error by roughly 45% on sunny outdoor scenes versus DiffusionLight.
-
LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields
A feed-forward transformer reconstructs shape, PBR materials, and view-dependent radiance from 3 to 6 posed images in under a second, rivaling slower optimization-based inverse rendering.
-
Digital Kitchen Remodeling: Editing and Relighting Intricate Indoor Scenes from a Single Panorama
A single-panorama kitchen remodeling pipeline with low-cost photometric calibration that recovers absolute radiance, validated at 3.988 cd/m² mean error on 141 scenes.
-
Event-assisted 12-stop HDR Imaging of Dynamic Scene
Event streams between extreme-exposure RGB frames enable explicit motion alignment, and a pre-trained diffusion prior fuses the brackets into ghost-reduced 12-stop HDR images; the authors also introduce the first 12-s...
-
Transforming Single Photon Camera Images to Color High Dynamic Range Images
On simulated single-photon camera data, Pix2PixHD colorization followed by DeepHDR reconstruction gives the best color HDR output, with a single-stage Pix2PixHD variant close behind.
Discussion (0). Continue with ORCID to comment.