AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement

• URL: http://arxiv.org/abs/2204.13983v1
• Date: Fri, 29 Apr 2022 10:16:57 GMT
• Title: AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement
• Authors: Canqian Yang, Meiguang Jin, Xu Jia, Yi Xu, Ying Chen
• Abstract summary: We present AdaInt, a novel mechanism to achieve a more flexible sampling point allocation by adaptively learning the non-uniform sampling intervals in the 3D color space. AdaInt could be implemented as a compact and efficient plug-and-play module for a 3D LUT-based method.
• Score: 28.977992864519948
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice. Previous works have made efforts to learn image-adaptive output color values of LUTs for flexible enhancement but neglect the importance of sampling strategy. They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform. Focusing on this problem, we present AdaInt (Adaptive Intervals Learning), a novel mechanism to achieve a more flexible sampling point allocation by adaptively learning the non-uniform sampling intervals in the 3D color space. In this way, a 3D LUT can increase its capability by conducting dense sampling in color ranges requiring highly non-linear transforms and sparse sampling for near-linear transforms. The proposed AdaInt could be implemented as a compact and efficient plug-and-play module for a 3D LUT-based method. To enable the end-to-end learning of AdaInt, we design a novel differentiable operator called AiLUT-Transform (Adaptive Interval LUT Transform) to locate input colors in the non-uniform 3D LUT and provide gradients to the sampling intervals. Experiments demonstrate that methods equipped with AdaInt can achieve state-of-the-art performance on two public benchmark datasets with a negligible overhead increase. Our source code is available at https://github.com/ImCharlesY/AdaInt.

Related papers

• VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation [69.68568248073747]
  We propose Pose-dependent Consistency Distillation Sampling (PCDS), a novel yet efficient objective for diffusion-based 3D generation tasks. PCDS builds the pose-dependent consistency function within diffusion trajectories, allowing to approximate true gradients through minimal sampling steps. For efficient generation, we propose a coarse-to-fine optimization strategy, which first utilizes 1-step PCDS to create the basic structure of 3D objects, and then gradually increases PCDS steps to generate fine-grained details.
  arXiv  Detail & Related papers  (2024-06-21T08:21:52Z)
• Tetrahedron Splatting for 3D Generation [39.24591650300784]
  Tetrahedron Splatting (TeT-Splatting) supports easy convergence during optimization, precise mesh extraction, and real-time rendering simultaneously. Our representation can be trained without mesh extraction, making the optimization process easier to converge.
  arXiv  Detail & Related papers  (2024-06-03T17:56:36Z)
• IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images [50.4538089115248]
  Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task. We propose a novel approach, IPoD, which harmonizes implicit field learning with point diffusion. Experiments conducted on the CO3D-v2 dataset affirm the superiority of IPoD, achieving 7.8% improvement in F-score and 28.6% in Chamfer distance over existing methods.
  arXiv  Detail & Related papers  (2024-03-30T07:17:37Z)
• DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mapping [46.80755234561584]
  Recent learning-based methods integrate neural implicit representations and optimizable feature grids to approximate surfaces of 3D scenes. In this work we depart from fitting LiDAR data exactly, instead letting the network optimize a non-metric monotonic implicit field defined in 3D space. Our algorithm achieves high-quality dense 3D mapping performance as captured by multiple quantitative and perceptual measures and visual results obtained for Mai City, Newer College, and KITTI benchmarks.
  arXiv  Detail & Related papers  (2024-03-26T09:58:06Z)
• CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs [65.80187860906115]
  We propose a novel approach to improve NeRF's performance with sparse inputs. We first adopt a voxel-based ray sampling strategy to ensure that the sampled rays intersect with a certain voxel in 3D space. We then randomly sample additional points within the voxel and apply a Transformer to infer the properties of other points on each ray, which are then incorporated into the volume rendering.
  arXiv  Detail & Related papers  (2024-03-25T15:56:17Z)
• pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction [26.72289913260324]
  pixelSplat is a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time.
  arXiv  Detail & Related papers  (2023-12-19T17:03:50Z)
• Learning Naturally Aggregated Appearance for Efficient 3D Editing [94.47518916521065]
  We propose to replace the color field with an explicit 2D appearance aggregation, also called canonical image. To avoid the distortion effect and facilitate convenient editing, we complement the canonical image with a projection field that maps 3D points onto 2D pixels for texture lookup. Our representation, dubbed AGAP, well supports various ways of 3D editing (e.g., stylization, interactive drawing, and content extraction) with no need of re-optimization.
  arXiv  Detail & Related papers  (2023-12-11T18:59:31Z)
• Mip-Splatting: Alias-free 3D Gaussian Splatting [52.366815964832426]
  3D Gaussian Splatting has demonstrated impressive novel view synthesis results, reaching high fidelity and efficiency. Strong artifacts can be observed when changing the sampling rate, eg, by changing focal length or camera distance. We find that the source for this phenomenon can be attributed to the lack of 3D frequency constraints and the usage of a 2D dilation filter.
  arXiv  Detail & Related papers  (2023-11-27T13:03:09Z)
• SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement [21.963622337032344]
  We present SepLUT (separable image-adaptive lookup table) to tackle the above limitations. Specifically, we separate a single color transform into a cascade of component-independent and component-correlated sub-transforms instantiated as 1D and 3D LUTs. In this way, the capabilities of two sub-transforms can facilitate each other, where the 3D LUT complements the ability to mix up color components.
  arXiv  Detail & Related papers  (2022-07-18T02:27:19Z)
• VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids [42.74658047803192]
  State-of-the-art 3D-aware generative models rely on coordinate-based parameterize 3D radiance fields. Existing approaches often render low-resolution feature maps and process them with an upsampling network to obtain the final image. In contrast to existing approaches, our method requires only a single forward pass to generate a full 3D scene.
  arXiv  Detail & Related papers  (2022-06-15T17:44:22Z)
• SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates [61.04823927283092]
  We propose to represent 3D shapes using 2D functions, where the output of the function at each 2D location is a sequence of line segments inside the shape. We implement this approach using a Seq2Seq model with attention, called SeqXY2SeqZ, which learns the mapping from a sequence of 2D coordinates along two arbitrary axes to a sequence of 1D locations along the third axis. Our experiments show that SeqXY2SeqZ outperforms the state-ofthe-art methods under widely used benchmarks.
  arXiv  Detail & Related papers  (2020-03-12T00:24:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.