AI Paper Atlas

Research map / 3D vision / 3D generation

GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth

Joaquin Gajardo, Michele Volpi, Marko Mihajlovic, Siyu Tang, Lukas Roth, Sergey Prokudin

ECCV 2026 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add organ latent code (ablation)GrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance / EPE: 1.05/3.44 -> 0.86/1.47Improved
add per-organ canonicalisation (ablation)GrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance / EPE: 0.96/4.23 -> 0.86/1.47Improved
use direct latent concatenation instead of FiLM conditioning (ablation)GrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance / EPE: 0.96/2.47 -> 0.86/1.47Improved
add multi-step Chamfer loss (ablation)GrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance / EPE: 0.91/1.89 -> 0.86/1.47Improved
add latent code regularisation L_code (ablation)GrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance / EPE: 0.88/1.74 -> 0.86/1.47Improved
use shared latent-conditioned field instead of per-organ MLPs (ablation)GrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance / EPE: 0.93/2.37 -> 0.86/1.47Improved
use shared latent-conditioned field instead of per-organ MLPs (ablation)GrowFields · TrackPlant3D per-organ sequences (45 organ seqs, mean)Chamfer distance / EPE: 0.94/2.44 -> 0.87/1.62Improved
replace ground-truth organ segmentation with automatic segmentationGrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance / EPE: 0.86/1.47 -> 0.86/1.42No clear effect
use part-aware compositional field versus full-plant baselinesGrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance: 615.7 -> 0.86Improved
use GrowFields instead of COAP for extrapolationGrowFields · TrackPlant3D extrapolated frames (mean)Chamfer distance: 451.09 -> 149.63Improved
use GrowFields instead of per-organ DPF for interpolationGrowFields · TrackPlant3D interpolated frames (full plant, mean)Chamfer distance: 10.24 -> 10.29Hurt
add Gaussian noise sigma 0.01 to input pointsGrowFields · TrackPlant3D full plant (8 test sequences, mean)Chamfer distance: 0.86 -> 1.08Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy