mlsanityData to 7 Oct 2026

ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability

arXiv 2608.09597 ↗First posted 10 Aug 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Producing a hand-buildable, colored brick model of a 3D object from a few casual photographs is a clean testbed for a broader challenge: generating 3D content that meets hard physical-assembly constraints under a discrete, budget-limited voxel grid. On a coarse lattice, visual resemblance and structural stability pull against each other, yet prior brick pipelines address only one side and treat voxelization as fixed preprocessing rather than a variable to optimize. We present ResemBrick, which couples the two. Budgeted occupancy completion reframes discretization as allocation: given a target occupied-voxel count, a single resolution-conditioned network decides in one feed-forward pass which surface voxels to fill for best appearance, one weight set spanning 13 resolutions. Buildability by construction then combines support- and look-ahead-aware greedy placement with a deterministic, provably terminating repair that grounds every floating component. Under a matched budget, ResemBrick surpasses existing voxel selectors in perceptual fidelity while uniquely reaching zero floating and zero unstable bricks on unfiltered held-out objects; as a complete pipeline, it attains the best perceptual fidelity among prior brick-construction systems. Our results point to treating discretization and assembly as tightly coupled stages rather than independent ones.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 49 references that are in the map. First posted on arXiv 10 Aug 2026.

Builds on

23 of 49 references.

References · 23

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  7. 2018Group Normalizationcited by 1,514
  8. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  9. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  10. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  11. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  12. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
11 more
  1. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  2. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  3. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  4. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 40
  5. 2025Generating Physically Stable and Buildable Brick Structures from Textcited by 23
  6. 2021Image2Lego: Customized LEGO Set Generation from Imagescited by 14
  7. 2026BrickNet: Graph-Backed Generative Brick Assemblycited by 5
  8. 2025Voxify3D: Pixel Art Meets Volumetric Renderingcited by 3
  9. 2026Rollback-Free Stable Brick Structures Generationcited by 2
  10. 2026DVD: Discrete Voxel Diffusion for 3D Generation and Editingcited by 2
  11. 2026BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ScaffoldM3C: A Multimodal Sequential Monte Carlo Framework for Generative Stable Construction Planningcited by 0