DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction

Kyungdon Joo, Jaehyeok Shim

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Abstract

lab.github.io/ditto (a) Input points (10K) (b) ConvONet [29] (c) POCO [1] (d) ALTO [44] (e) DITTO (ours) Figure 1. Scene-level 3D reconstruction comparison on the Synthetic Rooms dataset [29] . DITTO maximizes the benefits of both grid and point latents, thereby improving 3D surface reconstruction performance. We particularly focus on refining features based on point latents along with grid latents and integrating them (namely, dual and integrated latent topologies). This advancement enhances the ability to restore complex structures precisely, such as thin and intricate geometries, which posed challenges for previous methods.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.05005")
get_code_for_paper("2403.05005")
have("2403.05005")

Connect an agent — have() is free.