Liquid Neural Networks Improve Dynamic 3D Scene Reconstruction from Video
Researchers propose replacing standard neural networks with Liquid Neural Networks (LNNs) in 3D Gaussian Splatting, a technique for reconstructing dynamic scenes from monocular video. LNNs use continuous-time mathematical formulations that naturally smooth temporal changes rather than predicting discrete per-frame offsets. The approach matches or exceeds baseline performance on standard benchmarks, with particular improvements on scenes with complex articulated motion.
A new arXiv paper presents an architectural improvement to Deformable 3D Gaussian Splatting (D-3DGS), a method for reconstructing dynamic 3D scenes from single-camera video. The current approach uses a standard multilayer perceptron (MLP) that, despite being fitted to continuous time, effectively predicts independent per-frame deformations without explicit temporal continuity constraints. The researchers replace this with Liquid Neural Networks (LNNs) based on Closed-form Continuous-time (CfC) cells, which are the closed-form solutions of Liquid Time-constant ODEs. This design incorporates learned temporal smoothing directly into the network architecture through sigmoidal time gates that interpolate between hidden states, eliminating the need for numerical solvers. Testing on 15 standard benchmark scenes (eight from D-NeRF and seven from NeRF-DS), the liquid field approach matches or exceeds the MLP baseline overall, with the largest performance gains appearing on scenes featuring high-frequency articulated motion.
What's missing
The paper does not discuss computational cost comparisons between the LNN and MLP approaches, nor does it provide wall-clock time or memory usage metrics. Additionally, the generalization of the method to other dynamic scene reconstruction tasks beyond the tested benchmarks is not addressed.
What different sources said
- arXiv cs.AICenter
Liquid Neural Networks as a Drop-in Continuous-Time Deformation Field for Dynamic 3D Gaussian Splatting
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.