Problem Statement

Modern smartphone computational photography pipelines tackle two fundamental challenges in imaging: limited dynamic range and high sensor noise, especially in low-light conditions. Existing academic work (e.g., Blind2Unblind, GDP) largely targets smartphone RAW burst photography, which is difficult to replicate in an open research setting — the RAW burst pipelines of companies like Apple are closed-source, and capturing aligned multi-exposure bursts requires specialized hardware access.

Instead, we propose to leverage the physical advantages of a full-frame mirrorless camera (Sony ILCE-7M4) — its larger sensor provides substantially better per-pixel SNR and wider native dynamic range than any smartphone — to build and evaluate an HDR + denoising pipeline that is both reproducible and academically rigorous.

Our core question: For full-frame RAW capture, which combination of diffusion-based denoising and multi-exposure HDR merging produces the best final image quality?


Goals & Deliverables

Core Pipeline (Plan to Deliver)

1
RAW Denoising Evaluation
Capture a set of full-frame RAW images under controlled conditions. Apply two denoising strategies independently and evaluate quality with SNR, PSNR, and SSIM against a ground-truth clean reference:
  • Diffusion-based: GDP (Generative Diffusion Prior) applied to single RAW frames
  • Multi-frame averaging: Aligned multi-exposure stack merge for stationary scenes
2
Benchmark: Denoising × HDR Ordering
Build a benchmark comparing four pipeline variants across multiple test scenes:
Variant Description Key Trade-off
D only Diffusion denoising on each exposure, then HDR merge Best for dynamic scenes; no static requirement
D → M Diffusion first, then multi-frame merge Clean inputs to merger; may over-smooth
M → D Multi-frame merge first, then diffusion refinement Preserves structure; diffusion as post-processing
M only Multi-frame merge only (classical baseline) Requires static scene; no deep learning
3
Final HDR + Denoising Pipeline
Based on benchmark results, assemble the best-performing pipeline and demonstrate end-to-end HDR reconstruction with quantitative and qualitative evaluation.

Stretch Goals (Hope to Deliver)

A
Tone Mapping
Apply a tone mapping operator to the merged HDR output so the final image is visually faithful to human perception, with preserved highlight and shadow detail.
B
Custom-Trained Diffusion Denoiser
Train a diffusion model specifically on our captured full-frame RAW data, rather than relying solely on ImageNet-pretrained models, to better match our sensor's noise characteristics.
C
Natural Language Color Grading
Design a set of color-grading function calls (exposure, saturation, hue shift, LUT application, etc.), then connect them to an LLM so users can describe a desired look in plain language and receive a graded output automatically.

Proposed Pipeline

The figure below shows the full pipeline we plan to build. The innovative pipeline (top row) extends the baseline with white balance correction and optional LLM-driven color grading. The reproduced baseline (bottom row) follows the original Blind2Unblind + HDR merge approach for direct comparison.

— Our Innovative Pipeline —

Multi-Exposure Input
Short / Mid / Long LDR
White Balance
Color Temperature Correction
Diffusion Denoising
GDP / Blind2Unblind
HDR Merge
Camera Response Estimation + Fusion
Tone Mapping
LLM Color Grading
NL → Params → LUT
Final HDR Output

— Reproduced Baseline (from Papers) —

Same-Exposure Burst
burst photography
Blind2Unblind Denoising
Self-supervised, no pairs needed
HDR Merge
Frame alignment + fusion
Tone Mapping Output

Schedule

Week Tasks
Week 1 RAW data capture with Sony A7M4; set up denoising baselines (Blind2Unblind, GDP); implement evaluation metrics (SNR, PSNR, SSIM)
Week 2 Implement multi-frame HDR merging (camera response curve estimation + exposure fusion); white balance / color temperature correction module
Week 3 Build benchmark: run all four pipeline variants (D only, D→M, M→D, M only) on test dataset; quantitative + qualitative analysis
Week 4 Finalize best pipeline; stretch goals (tone mapping, LLM color grading); write-up and demo preparation

Resources

Reference Papers

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots
Wang et al., CVPR 2022   arXiv:2203.06967
Proposes a global-aware mask mapper and re-visible loss for self-supervised denoising without clean reference images, achieving state-of-the-art performance on real-world noise.
Generative Diffusion Prior for Unified Image Restoration and Enhancement (GDP)
Fei et al., CVPR 2023   arXiv:2304.01247
Exploits a pre-trained unconditional DDPM as a generative prior for unified image restoration (super-resolution, deblurring, inpainting, colorization, low-light enhancement, HDR recovery) in an unsupervised setting.
Burst Photography for High Dynamic Range and Low-Light Imaging on Mobile Cameras
Hasinoff et al., ACM TOG 2016   DOI:10.1145/2980179.2980254
Presents a practical burst photography pipeline for mobile imaging that combines frame alignment, robust merging, and HDR reconstruction to improve image quality in challenging low-light scenes.

Computing Platform

MacBook M4 Pro — 16/20-core GPU
MacBook M3 Pro — 16-core GPU
Lenovo Legion — NVIDIA RTX 5090 GPU

Hardware

Sony ILCE-7M4 (α7 IV) with Tamron 28–75mm f/2.8 G2
Full-frame 33 MP BSI-CMOS sensor. Larger pixel pitch and lower read noise compared to smartphone sensors, providing a stronger baseline SNR and enabling cleaner HDR bracket capture.