# A Little Bit More: Bitplane-Wise Bit-Depth Recovery

arXiv: https://arxiv.org/abs/2005.01091 · HTML: https://mlsanity.com/paper/2005.01091/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2020.

## Built on by (most cited first, 8 of 8)

- [HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization](https://mlsanity.com/paper/2105.13084/) (2021)
- [Learning sRGB-to-Raw-RGB De-rendering with Content-Aware Metadata](https://mlsanity.com/paper/2206.01813/) (2022)
- [Towards Lossless Implicit Neural Representation via Bit Plane Decomposition](https://mlsanity.com/paper/2502.21001/) (2025)
- [Learning Weighting Map for Bit-Depth Expansion within a Rational Range](https://mlsanity.com/paper/2204.12039/) (2022)
- [Bit-depth enhancement detection for compressed video](https://mlsanity.com/paper/2211.04799/) (2022)
- [Bit-depth color recovery via off-the-shelf super-resolution models](https://mlsanity.com/paper/2501.05611/) (2025)
- [Lossless-INR: Lossless Volumetric Implicit Neural Representations](https://mlsanity.com/paper/2607.18150/) (2026)
- [RAID: Towards Robust AI-Generated Image Detection with Bit-Reversed Images](https://mlsanity.com/paper/2607.28974/) (2026)

## Abstract (arXiv)

Imaging sensors digitize incoming scene light at a dynamic range of 10--12 bits (i.e., 1024--4096 tonal values). The sensor image is then processed onboard the camera and finally quantized to only 8 bits (i.e., 256 tonal values) to conform to prevailing encoding standards. There are a number of important applications, such as high-bit-depth displays and photo editing, where it is beneficial to recover the lost bit depth. Deep neural networks are effective at this bit-depth reconstruction task. Given the quantized low-bit-depth image as input, existing deep learning methods employ a single-shot approach that attempts to either (1) directly estimate the high-bit-depth image, or (2) directly estimate the residual between the high- and low-bit-depth images. In contrast, we propose a training and inference strategy that recovers the residual image bitplane-by-bitplane. Our bitplane-wise learning framework has the advantage of allowing for multiple levels of supervision during training and is able to obtain state-of-the-art results using a simple network architecture. We test our proposed method extensively on several image datasets and demonstrate an improvement from 0.5dB to 2.3dB PSNR over prior methods depending on the quantization level.