[ Audiovisual project / 002 ]
LOTHAL LAB · SANTIAGO ·
Continuous
River.
Two works produced in code, without generative AI.
- Type
- Algorithmic audiovisual artwork
- Author
- Lothal Lab
- Published
- Updated
- Output
- 2 audiovisual pieces
- Engine
- CAUCE
- Version
- Document 1.1
Summary
Continuous River brings together two works made with the same software: Ten Monet and Ten Van Gogh. Each transforms a painting series into a continuous flow of color masses.
Both works share the CAUCE engine and the same color-mass correspondence configuration. They run locally from recorded parameters and seeds, calculating every frame without generative AI models.
Questions
- 01
How can a painting sequence transform without stopping as it reaches each image?
- 02
How can two different corpora retain their visual identity while using the same engine?
Short answer
Transform without stopping the motion.
We represent every painting as color masses, solve correspondences between states and interpolate shape, pigment and movement within a global clock. The sequence crosses all ten works and returns to the beginning without pausing.
One architecture, two visual behaviors.
The engine keeps the same segmentation, correspondence and interpolation rules. The color structure, boundaries and masses of each corpus produce distinct responses without changing systems.
System architecture
There is no generative AI.
The project uses no diffusion, generative networks, language models or text prompts, and trains no model on the paintings. CAUCE works directly on the paintings’ pixels to segment masses, assign them and calculate trajectories.
- Corpora
- 10 Monet · 10 Van Gogh · public-domain reproductions
- CAUCE engine
- Segmentation · Hungarian assignment · SDF · Kubelka–Munk · curl noise
- Execution
- Local Python · recorded seeds · deterministic rendering · no frame-by-frame editing
Study I / Pictorial flow
Representation through color masses.
The corpus contains ten paintings by Claude Monet and ten by Vincent van Gogh, from public-domain reproductions available on Wikimedia Commons. Both series use the CAUCE engine’s meandro_fspline configuration.
Series order
The paintings are ordered to maximize color affinity between consecutive states. With ten images, the sequence is solved exactly through Held–Karp dynamic programming.
Decomposition
Mean shift reduces local variation. K-means groups pixels by color and position with k=13; watershed refines boundaries toward image gradients.
Correspondence
A cost matrix combines color, area and position. The Hungarian method solves assignments; the lineage supports appearances, disappearances, splits and merges.
World lines
Correspondences are chained into one trajectory per mass. The meander planner penalizes turns, abrupt speed changes and unnecessary travel.
Shape and pigment
Contours are interpolated through signed distance fields. Color uses a subtractive Kubelka–Munk approximation instead of additive RGB fading.
Continuity and closure
A curl-noise field sustains rotational movement. One global clock joins every segment and returns the final state to the first.
Audiovisual composition
Two works.
The videos are hosted on media.ymo.cl and load when playback begins.
Ten Monet
Ten paintings · 40 s · 1350 × 1080 · 60 fps master · seamless loop · silent
The engine processes soft gradients and diffuse boundaries between color regions.
Ten Van Gogh
Ten paintings · 40 s · 1350 × 1080 · 60 fps master · seamless loop · silent
The same configuration is applied to works with stronger contrast, impasto and brush direction.
Verification
Continuity criterion.
The judge calculates the mean absolute difference between each pair of frames. A render is rejected when the minimum value around a transition is below 0.5 times the clip median. The test detects accidental pauses; it does not evaluate visual quality.
This is an internal project metric, not an external standard.
Design decisions
The corpus selection, correspondences, trajectories and rejection criteria were defined during development.
These decisions are recorded in the code and its parameters, rather than added through later video editing or instructions sent to a generative model.
Scope and limitations
Study limitations.
- The metrics verify continuity and boundary fit; they do not measure artistic quality or audience response.
- The temporal-change threshold is an operational project criterion, not an external standard.
- Kubelka–Munk is used as a subtractive approximation without spectral calibration against physical pigments.
- Exact reproduction requires the same seed, dependency versions and compute path.
- The individual URL for each Wikimedia Commons reproduction remains to be recorded.
Painting corpus
Works used.
Claude Monet
Impression, Sunrise · The Japanese Bridge · Poppies · The Magpie · Haystack in Sunlight · Houses of Parliament · San Giorgio Maggiore · Terrace at Sainte-Adresse · Cliff Walk at Pourville · The Saint-Lazare Station.
Vincent van Gogh
The Starry Night · Starry Night Over the Rhône · The Harvest · Fishing Boats · Irises · Almond Blossom · Wheatfield with Crows · The Bedroom · Wheat Field with Cypresses · The Red Vineyard.
Reproductions gathered from Wikimedia Commons. Titles are normalized in English for this document.
References
Technical references.
- 01
Held, M. and Karp, R. M. (1962). A Dynamic Programming Approach to Sequencing Problems.
- 02
Kuhn, H. W. (1955). The Hungarian Method for the Assignment Problem.
- 03
Kubelka, P. and Munk, F. (1931). An Article on Optics of Paint Layers.
- 04
Bridson, R., Houriham, J. and Nordenstam, M. (2007). Curl-Noise for Procedural Fluid Flow.









